CN111459832A - Heterogeneous compilation algorithm feasibility evaluation method and system - Google Patents
Heterogeneous compilation algorithm feasibility evaluation method and system Download PDFInfo
- Publication number
- CN111459832A CN111459832A CN202010284688.6A CN202010284688A CN111459832A CN 111459832 A CN111459832 A CN 111459832A CN 202010284688 A CN202010284688 A CN 202010284688A CN 111459832 A CN111459832 A CN 111459832A
- Authority
- CN
- China
- Prior art keywords
- server software
- heterogeneous
- heterogeneous server
- software
- complexity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Preventing errors by testing or debugging software
- G06F11/3604—Software analysis for verifying properties of programs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Preventing errors by testing or debugging software
- G06F11/3604—Software analysis for verifying properties of programs
- G06F11/3616—Software analysis for verifying properties of programs using software metrics
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a heterogeneous compilation algorithm feasibility evaluation method and a system, wherein the method comprises the following steps: determining the isomerism of heterogeneous server software and determining a performance loss value of the heterogeneous server software; calculating the heterogeneous cost-efficiency ratio of the heterogeneous server software based on the ratio of the performance loss value to the heterogeneity; and obtaining the evaluation result of the feasibility of the heterogeneous compiling algorithm based on the heterogeneous cost-to-efficiency ratio. The invention can quantitatively evaluate the actual benefit generated by each heterogeneous software compiling algorithm by quantifying the heterogeneity of the server software in the system and the performance loss values of the server software before and after diversified compiling, and provides data support for further selecting the heterogeneous server software to construct the pseudo-structured web server.
Description
Technical Field
The invention relates to the technical field of network security, in particular to a heterogeneous compilation algorithm feasibility evaluation method and system.
Background
With the increasing importance of the country on the network space security, more security defense technologies are gradually emerging. As an innovative security defense technology, the network space mimicry defense technology adopts a core architecture of Dynamic Heterogeneous Redundancy (DHR), so that the probability of common-mode faults of the system due to design defects (or unwanted redundant functions or 'dark functions') is reduced and the security of the system is further improved on the premise that functional equivalence and the high probability of calculation results of all executors are ensured to be correct.
The method comprises the steps of simulating a Web server constructed by a plurality of heterogeneous Web service executors, wherein the executors are usually manufactured by COTS (code of lots of materials) level components of different manufacturers and different versions and models or are used for realizing self heterogeneity and redundancy by means of a diversified compiling algorithm.
However, the diversified compiling algorithm is implemented as software diversity, and its main purpose is to change the structural characteristics of the software itself as much as possible to increase the probability of the reverse success of the attacker, and actually the influence of the complex software structure on the software operation performance is not considered. In the current network environment, not only the security gain brought by the pseudo-structured web server is considered, but also the running performance of the pseudo-structured web server is ensured.
Therefore, how to effectively evaluate the feasibility of the heterogeneous compilation algorithm is a problem to be solved.
Disclosure of Invention
In view of this, the invention provides a heterogeneous compilation algorithm feasibility evaluation method, which can quantitatively evaluate the actual benefits that each heterogeneous software compilation algorithm can produce by quantifying the heterogeneity of server software in a system and the performance loss values of the server software before and after diversified compilation, and provide data support for further selecting the heterogeneous server software to construct a web server of a proposed structure.
The invention provides a heterogeneous compilation algorithm feasibility evaluation method, which comprises the following steps:
determining the heterogeneity of heterogeneous server software;
determining a performance loss value of the heterogeneous server software;
calculating the heterogeneous cost-efficiency ratio of the heterogeneous server software based on the ratio of the performance loss value to the heterogeneity;
and obtaining the evaluation result of the feasibility of the heterogeneous compiling algorithm based on the heterogeneous cost-to-efficiency ratio.
Preferably, the determining the heterogeneity of the heterogeneous server software comprises:
calculating the complexity of the heterogeneous server software;
calculating the difference of the heterogeneous server software;
according to the formula
Calculating the heterogeneity of the heterogeneous server software, wherein EHiRepresenting heterogeneous Server software EiIs the isomerism of EC0Indicating non-heterogeneous server software E0Complexity, EC ofiRepresenting heterogeneous Server software EiComplexity of, EDiRepresenting heterogeneous Server software EiAnd non-heterogeneous Server software E0The difference in the ratio of (a) to (b).
Preferably, the calculating complexity of the heterogeneous server software comprises:
constructing complexity index vectors
Wherein C isi＝(ci1，ci2…，cim) Representing heterogeneous Server software EiComplexity index vector of (1), C0Indicating non-heterogeneous server software E0A complexity index vector of;
performing principal component analysis on the complexity index to obtain the calculation weight of each complexity index
According to the formula
Calculating to obtain heterogeneous server software EiThe complexity of (a).
Preferably, the computing the differences of the heterogeneous server software comprises:
compute heterogeneous Server software EiAnd non-heterogeneous Server software E0Inter-compilation algorithm variability Edai；
For heterogeneous server software EiAnd non-heterogeneous Server software E0The binary files are evaluated differently to obtain an evaluation result Edbi；
According to the formula EDi＝μ1·Edai+μ2·EdbiThe method adopts a weighting calculation mode to carry out weighting calculation on the heterogeneous server software EiAnd non-heterogeneous Server software E0The differences are quantified to obtain the differences ED of the heterogeneous server softwareiWherein, mu1And mu2Is the set weight.
Preferably, the determining the performance loss value of the heterogeneous server software comprises:
according to the formula
Quantifying the performance loss value of the heterogeneous server software by adopting the standardized Euclidean distance to obtain the performance loss value of the heterogeneous server software, wherein the PsriIs a heterogeneous server software EiThe value of the loss of performance of (c),
is a performance feature vector ViAnd B0Standard deviation between attribute eigenvalues, Vi＝(vi1，vi2，…，vip) Representing heterogeneous Server software EiPerformance feature vector of, B0＝(b1，b2，…bp) Indicating non-heterogeneous server software E0The performance characteristic vector of (2) is used as a reference for calculating the performance loss value of the heterogeneous software.
A heterogeneous compilation algorithm feasibility assessment system, comprising:
the first determining module is used for determining the heterogeneity of the heterogeneous server software;
the second determining module is used for determining the performance loss value of the heterogeneous server software;
the calculation module is used for calculating the heterogeneous cost-efficiency ratio of the heterogeneous server software based on the ratio of the performance loss value to the heterogeneity;
and the evaluation module is used for obtaining the evaluation result of the feasibility of the heterogeneous compiling algorithm based on the heterogeneous cost-to-efficiency ratio.
Preferably, the first determining module comprises:
the first computing unit is used for computing the complexity of the heterogeneous server software;
the second calculation unit is used for calculating the difference of the heterogeneous server software;
a third calculation unit for calculating
Calculating the heterogeneity of the heterogeneous server software, wherein EHiRepresenting heterogeneous Server software EiIs the isomerism of EC0Indicating non-heterogeneous server software E0Complexity, EC ofiRepresenting heterogeneous Server software EiComplexity of, EDiRepresenting heterogeneous Server software EiAnd non-heterogeneous Server software E0The difference in the ratio of (a) to (b).
Preferably, the first computing unit is specifically configured to:
constructing complexity index vectors
Wherein C isi＝(ci1，ci2…，cim) Representing heterogeneous Server software EiComplexity index vector of (1), C0Indicating non-heterogeneous server software E0A complexity index vector of;
performing principal component analysis on the complexity index to obtain the calculation weight of each complexity index
According to the formula
Calculating to obtain heterogeneous server software EiThe complexity of (a).
Preferably, the second computing unit is specifically configured to:
compute heterogeneous Server software EiAnd non-heterogeneous Server software E0Inter-compilation algorithm variability Edai；
For heterogeneous server software EiAnd non-heterogeneous Server software E0The binary files are evaluated differently to obtain an evaluation result Edbi；
According to the formula EDi＝μ1·Edai+μ2·EdbiThe method adopts a weighting calculation mode to carry out weighting calculation on the heterogeneous server software EiAnd non-heterogeneous Server software E0The differences are quantified to obtain the differences ED of the heterogeneous server softwareiWherein, mu1And mu2Is the set weight.
Preferably, the second determining module is specifically configured to:
according to the formula
Quantifying the performance loss value of the heterogeneous server software by adopting the standardized Euclidean distance to obtain the performance loss value of the heterogeneous server software, wherein the PsriIs a heterogeneous server software EiThe value of the loss of performance of (c),
is a performance feature vector ViAnd B0Standard deviation between attribute eigenvalues, Vi＝(vi1，vi2，…，vip) Representing heterogeneous Server software EiPerformance feature vector of, B0＝(b1，b2，…bp) Representing non-heterogeneous servicesSoftware of device E0The performance characteristic vector of (2) is used as a reference for calculating the performance loss value of the heterogeneous software.
In summary, the invention discloses a method for evaluating the feasibility of a heterogeneous compilation algorithm, which comprises the steps of firstly determining the heterogeneity of heterogeneous server software and determining a performance loss value of the heterogeneous server software when the feasibility of the heterogeneous compilation algorithm needs to be evaluated; and then calculating to obtain the heterogeneous cost-efficiency ratio of the heterogeneous server software based on the ratio of the performance loss value to the heterogeneity, and obtaining the evaluation result of the feasibility of the heterogeneous compiling algorithm based on the heterogeneous cost-efficiency ratio. The invention can quantitatively evaluate the actual benefit generated by each heterogeneous software compiling algorithm by quantifying the heterogeneity of the server software in the system and the performance loss values of the server software before and after diversified compiling, and provides data support for further selecting the heterogeneous server software to construct the pseudo-structured web server.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of a method of evaluating feasibility of a heterogeneous compilation algorithm according to embodiment 1 of the present disclosure;
FIG. 2 is a flowchart of a method of evaluating feasibility of a heterogeneous compilation algorithm according to embodiment 2 of the present disclosure;
fig. 3 is a schematic structural diagram of a heterogeneous compilation algorithm feasibility assessment system 1 according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of a heterogeneous compilation algorithm feasibility assessment system 21 according to an embodiment of the present disclosure.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, which is a flowchart of a method in embodiment 1 of the feasibility assessment method for heterogeneous compilation algorithm disclosed in the present invention, the method may include the following steps:
s101, determining the isomerism of heterogeneous server software;
when the feasibility of the heterogeneous compiling algorithm needs to be evaluated, firstly, the heterogeneity EH of the heterogeneous server software is quantifiedi。
S102, determining a performance loss value of the heterogeneous server software;
meanwhile, performance loss value Psr of server software before and after diversified compilation is quantizedi。
S103, calculating the heterogeneous cost-effectiveness ratio of the heterogeneous server software based on the ratio of the performance loss value to the heterogeneity;
when determining the isomerism EH of the heterogeneous server softwareiAnd performance loss value Psr of heterogeneous server softwareiThen, according to the formula Hproi＝Psri/EHiCalculating to obtain heterogeneous cost-to-efficiency ratio Hpro of heterogeneous server softwarei。
And S104, obtaining the evaluation result of the feasibility of the heterogeneous compiling algorithm based on the heterogeneous cost-efficiency ratio.
According to the loss of performance value PsriAnd isomeric EHiThe value-taking state of the server software and the heterogeneous cost-effectiveness ratio of the server software are in three extreme states. When Psr isi0 but EHiWhen not equal to 0, HproiWhen the value is 0, the electrode is called as a positive electrode state; when Psr isiNot equal to 0 but EHiWhen 0, Hproi→ infinity, the present invention is referred to as the negative state; when Psr isi0 but EHiWhen 0, the present invention is referred to as the invalid state.
When the heterogeneous cost-to-efficiency ratio is in a positive state, the compiling algorithm corresponding to the heterogeneous server software can generate extremely high benefit in practical application, and is more suitable for generating the heterogeneous executors in the pseudo-structured web server. When the heterogeneous cost-effectiveness ratio is in a negative state, the compiling algorithm corresponding to the heterogeneous server software is extremely low in benefit in practical application, and is not suitable for generating the heterogeneous executors in the pseudo-structure web server. Furthermore, when constructing heterogeneous web service executors, the corresponding compilation algorithm between the positive state and the invalid state should be biased.
In addition, for two heterogeneous server software EiAnd EjIf the precondition Psr is presenti＝PsrjThen HproiAnd HprojThe greater the phase difference, the more heterogeneous server software EiAnd EjThe greater the isomerism between. At this time, the two corresponding compiling algorithms are more suitable for constructing heterogeneous web service executors for different execution body pools.
In summary, in the above embodiment, when the feasibility of the heterogeneous compilation algorithm needs to be evaluated, the heterogeneity of the heterogeneous server software is determined first, and the performance loss value of the heterogeneous server software is determined; and then calculating to obtain the heterogeneous cost-efficiency ratio of the heterogeneous server software based on the ratio of the performance loss value to the heterogeneity, and obtaining the evaluation result of the feasibility of the heterogeneous compiling algorithm based on the heterogeneous cost-efficiency ratio. The method can quantitatively evaluate the actual benefits generated by each heterogeneous software compiling algorithm by quantifying the heterogeneity of the server software in the system and the performance loss values of the server software before and after diversified compiling, and provides data support for further selecting the heterogeneous server software to construct the web server with the mimicry structure.
As shown in fig. 2, which is a flowchart of a method of evaluating feasibility of a heterogeneous compilation algorithm in embodiment 2 of the present disclosure, the method may include the following steps:
s201, calculating the complexity of heterogeneous server software;
when the feasibility of the heterogeneous compilation algorithm needs to be evaluated, the complexity EC of the heterogeneous server software is calculated firstlyi. Complexity EC in computing heterogeneous server softwareiIn the first place, the inventionConstructing complexity index vector by selecting program capacity, Jcc instruction number, Call instruction number, control flow basic block number, edge number and loop complexity and other indexes, and recording the complexity index vector as
Wherein C isi＝(ci1，ci2…，cim) Representing heterogeneous Server software EiComplexity index vector of (1), C0Indicating non-heterogeneous server software E0The complexity index vector of (2). Then, the complexity indexes are subjected to principal component analysis to obtain the calculation weight of each index
Finally according to the formula
Calculating to obtain heterogeneous server software EiThe complexity of (a).
S202, calculating the difference of heterogeneous server software;
then, calculating the difference ED of the heterogeneous server softwarei. Computing differential ED of heterogeneous server softwareiIn time, the invention quantifies the difference between the binary file of the software and the compiling algorithm used by the software. Different binary files mean inconsistency of reverse operations of an attacker, and the heterogeneity provided by different compiling algorithms to software can be embodied at different levels. By combining the attack and self angles, the difference between heterogeneous server software can be more comprehensively explained.
For the difference of the compiling algorithms, for a given server software, the algorithm after one or more diversified compiling algorithms are combined can be adopted for carrying out isomerism when diversified compiling is carried out, and the heterogeneous server software E is usediThe adopted coding algorithm formalized representation is a coding algorithm vector
Wherein A isi＝(ai0，ai1，ai2，…，aim) And a is ai0Representing non-heterogeneous server software E0The adopted traditional compiling algorithm rho0。
If aij1 means that the compilation algorithm ρ is adopted in the diversified compilation process of the application programjOn the contrary, if aij0 means that the coding algorithm ρ is not usedj. In the calculation process of the difference of the compiling algorithm between server software, AiAnd (i ═ 0, 1, …, n) can be calculated as a feature vector for each piece of software.
The invention measures the difference of the compiling algorithm based on the cosine similarity of the compiling algorithm vector between the server software and mainly aims at the heterogeneous server software EiAnd non-heterogeneous Server software E0The difference of the compiling algorithms between the two is quantified.
Assuming that the complexity provided by each compiling algorithm to the software keeps a stable value and does not interfere with each other, the specific calculation formula is as follows:
wherein, EdaiIs a heterogeneous server software EiAnd non-heterogeneous Server software E0The difference of compiling algorithms between the two, and 0 is not less than Edai≤1。
Furthermore, the invention couples the heterogeneous server software E by means of the disassembling tool IDA and the BinDiffiAnd non-heterogeneous Server software E0The binary files are evaluated differently, and the evaluation result is recorded as Edbi。
Finally, according to the formula EDi＝μ1·Edai+μ2·EdbiThe method adopts a weighting calculation mode to carry out weighting calculation on the heterogeneous server software EiAnd non-heterogeneous Server software E0The differences are quantified to obtain the differences ED of the heterogeneous server softwareiWherein, mu1And mu2For the weight value to be set, the weight value can be set toμ1＝0.17，μ20.83 and ED is not more than 0i≤1。
S203, according to the formula
Calculating the heterogeneity of the heterogeneous server software, wherein EHiRepresenting heterogeneous Server software EiIs the isomerism of EC0Indicating non-heterogeneous server software E0Complexity, EC ofiRepresenting heterogeneous Server software EiComplexity of, EDiRepresenting heterogeneous Server software EiAnd non-heterogeneous Server software E0Difference of (2);
in calculating the complexity EC of heterogeneous server softwareiDifferencing ED with heterogeneous Server softwareiThen according to the formula
Calculating the heterogeneity of the heterogeneous server software, wherein EHiRepresenting heterogeneous Server software EiIs the isomerism of EC0Indicating non-heterogeneous server software E0Complexity, EC ofiRepresenting heterogeneous Server software EiComplexity of, EDiRepresenting heterogeneous Server software EiAnd non-heterogeneous Server software E0The difference in the ratio of (a) to (b).
S204, according to the formula
Quantifying the performance loss value of the heterogeneous server software by adopting a standardized Euclidean distance to obtain the performance loss value of the heterogeneous server software, wherein the performance loss value of the heterogeneous server software is PsriIs a heterogeneous server software EiThe value of the loss of performance of (c),
is a performance feature vector ViAnd B0Standard deviation between attribute eigenvalues, Vi＝(vi1，vi2，…，vip) Representing heterogeneous Server software EiPerformance feature vector of, B0＝(b1，b2，…bp) Indicating non-heterogeneous server software E0The performance characteristic vector is used as a reference for calculating the performance loss value of the heterogeneous software;
in order to better evaluate the performance change of the server software after diversified compilation, the invention provides a concept of software performance loss value. And calculating the performance loss of each diversified and compiled server software by taking the non-heterogeneous version of the server software as a reference. In order to reduce the influence of the distribution of each performance index on the performance loss value calculation result, the performance loss value of the heterogeneous server software is quantized by adopting the standardized Euclidean distance. Heterogeneous Server software EiThe formula for calculating the performance loss value of (a) is as follows:
wherein, PsriIs a heterogeneous server software EiThe value of the loss of performance of (c),
is a performance feature vector ViAnd B0Standard deviation between attribute eigenvalues, Vi＝(vi1，vi2，…，vip) Representing heterogeneous Server software EiPerformance feature vector of, B0＝(b1，b2，…bp) Indicating non-heterogeneous server software E0The performance characteristic vector of (2) is used as a reference for calculating the performance loss value of the heterogeneous software.
S205, calculating the heterogeneous cost-efficiency ratio of the heterogeneous server software based on the ratio of the performance loss value to the heterogeneity;
when determining the isomerism EH of the heterogeneous server softwareiAnd performance loss value Psr of heterogeneous server softwareiThen, according to the formula Hproi＝Psri/EHiCalculating to obtain heterogeneous cost-to-efficiency ratio Hpro of heterogeneous server softwarei。
And S206, obtaining the evaluation result of the feasibility of the heterogeneous compiling algorithm based on the heterogeneous cost-to-efficiency ratio.
According to the loss of performance value PsriAnd isomeric EHiThe value-taking state of the server software and the heterogeneous cost-effectiveness ratio of the server software are in three extreme states. When Psr isi0 but eHiWhen not equal to 0, HproiWhen the value is 0, the electrode is called as a positive electrode state; when Psr isiNot equal to 0 but EHiWhen 0, Hproi→ infinity, the present invention is referred to as the negative state; when Psr isi0 but EHiWhen 0, the present invention is referred to as the invalid state.
When the heterogeneous cost-to-efficiency ratio is in a positive state, the compiling algorithm corresponding to the heterogeneous server software can generate extremely high benefit in practical application, and is more suitable for generating the heterogeneous executors in the pseudo-structured web server. When the heterogeneous cost-effectiveness ratio is in a negative state, the compiling algorithm corresponding to the heterogeneous server software is extremely low in benefit in practical application, and is not suitable for generating the heterogeneous executors in the pseudo-structure web server. Furthermore, when constructing heterogeneous web service executors, the corresponding compilation algorithm between the positive state and the invalid state should be biased.
In addition, for two heterogeneous server software EiAnd EjIf the precondition Psr is presenti＝PsrjThen HproiAnd HprojThe greater the phase difference, the more heterogeneous server software EiAnd EjThe greater the isomerism between. At this time, the two corresponding compiling algorithms are more suitable for constructing heterogeneous web service executors for different execution body pools.
In a specific application, the method divides different stages according to the heterogeneous cost-to-efficiency ratio of heterogeneous software. When the heterogeneous cost-to-efficiency ratio value is within the range of 0-2, the heterogeneous server software is considered to be in a normal state, and the corresponding diversified compiling algorithm can be used for constructing a heterogeneous web service execution body; when the heterogeneous cost-to-efficiency ratio value is within the range of 2-4, the heterogeneous server software is considered to be in an unstable state; when the heterogeneous cost-to-efficiency ratio value is more than 4, the heterogeneous server software is considered to be in an unavailable state, the corresponding diversified compiling algorithm cannot be used for constructing a heterogeneous web service execution body, the performance of the web server with a mimicry structure can be seriously influenced, meanwhile, response overtime can cause more false alarms to be generated by the system, and certain interference is caused to a voting mechanism of the system.
In summary, the heterogeneous cost-effectiveness ratio of the compiling algorithm is calculated by quantifying the heterogeneous performance loss value and the performance loss value of the compiled software, and finally the calculation formula of the heterogeneous cost-effectiveness ratio is provided, so that the actual benefit generated by the diversified compiling strategy can be intuitively evaluated, and meanwhile, the method has certain universality, not only can be applied to a pseudo-structured web server, but also can be applied to other safety systems with heterogeneous redundancy characteristics.
As shown in fig. 3, which is a schematic structural diagram of a heterogeneous compilation algorithm feasibility assessment system embodiment 1 disclosed in the present invention, the system may include:
a first determining module 301, configured to determine heterogeneity of heterogeneous server software;
when the feasibility of the heterogeneous compiling algorithm needs to be evaluated, firstly, the heterogeneity EH of the heterogeneous server software is quantifiedi。
A second determining module 302, configured to determine a performance loss value of the heterogeneous server software;
meanwhile, performance loss value Psr of server software before and after diversified compilation is quantizedi。
The calculating module 303 is configured to calculate, based on the ratio of the performance loss value to the heterogeneity, a heterogeneous cost-to-efficiency ratio of the heterogeneous server software;
when determining the isomerism EH of the heterogeneous server softwareiAnd performance loss value Psr of heterogeneous server softwareiThen, according to the formula Hproi＝Psri/EHiCalculating to obtain heterogeneous cost-to-efficiency ratio Hpro of heterogeneous server softwarei。
And the evaluation module 304 is configured to obtain an evaluation result of the feasibility of the heterogeneous compiling algorithm based on the heterogeneous cost-to-efficiency ratio.
According to the loss of performance value PsriAnd isomeric EHiThe heterogeneous cost-to-efficiency ratio of server software presents three extreme states. When Psr isi0 but EHiWhen not equal to 0, HproiWhen the value is 0, the electrode is called as a positive electrode state; when Psr isiNot equal to 0 but EHiWhen 0, Hproi→ infinity, the present invention is referred to as the negative state; when Psr isi0 but EHiWhen 0, the present invention is referred to as the invalid state.
When the heterogeneous cost-to-efficiency ratio is in a positive state, the compiling algorithm corresponding to the heterogeneous server software can generate extremely high benefit in practical application, and is more suitable for generating the heterogeneous executors in the pseudo-structured web server. When the heterogeneous cost-effectiveness ratio is in a negative state, the compiling algorithm corresponding to the heterogeneous server software is extremely low in benefit in practical application, and is not suitable for generating the heterogeneous executors in the pseudo-structure web server. Furthermore, when constructing heterogeneous web service executors, the corresponding compilation algorithm between the positive state and the invalid state should be biased.
In addition, for two heterogeneous server software EiAnd EjIf the precondition Psr is presenti＝PsrjThen HproiAnd HprojThe greater the phase difference, the more heterogeneous server software EiAnd EjThe greater the isomerism between. At this time, the two corresponding compiling algorithms are more suitable for constructing heterogeneous web service executors for different execution body pools.
In summary, in the above embodiment, when the feasibility of the heterogeneous compilation algorithm needs to be evaluated, the heterogeneity of the heterogeneous server software is determined first, and the performance loss value of the heterogeneous server software is determined; and then calculating to obtain the heterogeneous cost-efficiency ratio of the heterogeneous server software based on the ratio of the performance loss value to the heterogeneity, and obtaining the evaluation result of the feasibility of the heterogeneous compiling algorithm based on the heterogeneous cost-efficiency ratio. The method can quantitatively evaluate the actual benefits generated by each heterogeneous software compiling algorithm by quantifying the heterogeneity of the server software in the system and the performance loss values of the server software before and after diversified compiling, and provides data support for further selecting the heterogeneous server software to construct the web server with the mimicry structure.
As shown in fig. 4, which is a schematic structural diagram of a heterogeneous compilation algorithm feasibility assessment system embodiment 2 disclosed in the present invention, the system may include:
a first computing unit 401, configured to compute complexity of heterogeneous server software;
when the feasibility of the heterogeneous compilation algorithm needs to be evaluated, the complexity EC of the heterogeneous server software is calculated firstlyi. Complexity EC in computing heterogeneous server softwareiFirstly, selecting program capacity, Jcc instruction quantity, Call instruction quantity, control flow basic block quantity, edge quantity and loop complexity to construct complexity index vector, recording said vector as
Wherein C isi＝(ci1，ci2…，cim) Representing heterogeneous Server software EiComplexity index vector of (1), C0Indicating non-heterogeneous server software E0The complexity index vector of (2). Then, the complexity indexes are subjected to principal component analysis to obtain the calculation weight of each index
Finally according to the formula
Calculating to obtain heterogeneous server software EiThe complexity of (a).
A second calculating unit 402, configured to calculate differences of the heterogeneous server software;
then, calculating the difference ED of the heterogeneous server softwarei. Computing differential ED of heterogeneous server softwareiIn time, the invention quantifies the difference between the binary file of the software and the compiling algorithm used by the software. Different binary files mean inconsistency of reverse operations of an attacker, and the heterogeneity provided by different compiling algorithms to software can be embodied at different levels. By combining the attack and self angles, the difference between heterogeneous server software can be more comprehensively explained.
Wherein for the compilation calculationFor the difference of the method, for a given server software, when diversified compilation is carried out, one or more algorithms combined by diversified compilation algorithms can be adopted for carrying out isomerism, and the heterogeneous server software E isiThe adopted coding algorithm formalized representation is a coding algorithm vector
Wherein A isi＝(ai0，ai1，ai2，…，aim) And a is ai0Representing non-heterogeneous server software E0The adopted traditional compiling algorithm rho0。
If aij1 means that the compilation algorithm ρ is adopted in the diversified compilation process of the application programjOn the contrary, if aij0 means that the coding algorithm ρ is not usedj. In the calculation process of the difference of the compiling algorithm between server software, AiAnd (i ═ 0, 1, …, n) can be calculated as a feature vector for each piece of software.
The invention measures the difference of the compiling algorithm based on the cosine similarity of the compiling algorithm vector between the server software and mainly aims at the heterogeneous server software EiAnd non-heterogeneous Server software E0The difference of the compiling algorithms between the two is quantified.
Assuming that the complexity provided by each compiling algorithm to the software keeps a stable value and does not interfere with each other, the specific calculation formula is as follows:
wherein, EdaiIs a heterogeneous server software EiAnd non-heterogeneous Server software E0The difference of compiling algorithms between the two, and 0 is not less than Edai≤1。
Furthermore, the invention couples the heterogeneous server software E by means of the disassembling tool IDA and the BinDiffiAnd non-heterogeneous Server software E0Evaluating the difference of binary files and evaluating the evaluation resultIs recorded as Edbi。
Finally, according to the formula EDi＝μ1·Edai+μ2·EdbiThe method adopts a weighting calculation mode to carry out weighting calculation on the heterogeneous server software EiAnd non-heterogeneous Server software E0The differences are quantified to obtain the differences ED of the heterogeneous server softwareiWherein, mu1And mu2For the weight value to be set, the weight value can be set to μ1＝0.17，μ20.83 and ED is not more than 0i≤1。
A third calculation unit 403 for calculating according to the formula
Calculating the heterogeneity of the heterogeneous server software, wherein EHiRepresenting heterogeneous Server software EiIs the isomerism of EC0Indicating non-heterogeneous server software E0Complexity, EC ofiRepresenting heterogeneous Server software EiComplexity of, EDiRepresenting heterogeneous Server software EiAnd non-heterogeneous Server software E0Difference of (2);
in calculating the complexity EC of heterogeneous server softwareiDifferencing ED with heterogeneous Server softwareiThen according to the formula
Calculating the heterogeneity of the heterogeneous server software, wherein EHiRepresenting heterogeneous Server software EiIs the isomerism of EC0Indicating non-heterogeneous server software E0Complexity, EC ofiRepresenting heterogeneous Server software EiComplexity of, EDiRepresenting heterogeneous Server software EiAnd non-heterogeneous Server software E0The difference in the ratio of (a) to (b).
A second determining module 404 for determining the relationship
Quantifying the performance loss value of the heterogeneous server software by adopting a standardized Euclidean distance to obtain the performance loss value of the heterogeneous server software, wherein the performance loss value of the heterogeneous server software is PsriIs a heterogeneous server software EiThe value of the loss of performance of (c),
is a performance feature vector ViAnd B0Standard deviation between attribute eigenvalues, Vi＝(vi1，vi2，…，vip) Representing heterogeneous Server software EiPerformance feature vector of, B0＝(b1，b2，…bp) Indicating non-heterogeneous server software E0The performance characteristic vector is used as a reference for calculating the performance loss value of the heterogeneous software;
in order to better evaluate the performance change of the server software after diversified compilation, the invention provides a concept of software performance loss value. And calculating the performance loss of each diversified and compiled server software by taking the non-heterogeneous version of the server software as a reference. In order to reduce the influence of the distribution of each performance index on the performance loss value calculation result, the performance loss value of the heterogeneous server software is quantized by adopting the standardized Euclidean distance. Heterogeneous Server software EiThe formula for calculating the performance loss value of (a) is as follows:
wherein, PsriIs a heterogeneous server software EiThe value of the loss of performance of (c),
is a performance feature vector ViAnd B0Standard deviation between attribute eigenvalues, Vi＝(vi1，vi2，…，vip) Representing heterogeneous Server software EiPerformance feature vector of, B0＝(b1，b2，…bp) Indicating non-heterogeneous server software E0The performance characteristic vector of (2) is used as a reference for calculating the performance loss value of the heterogeneous software.
A calculating module 405, configured to calculate, based on a ratio of the performance loss value to the heterogeneity, a heterogeneous cost-to-efficiency ratio of the heterogeneous server software;
when determining the isomerism EH of the heterogeneous server softwareiAnd performance loss value Psr of heterogeneous server softwareiThen, according to the formula Hproi＝Psri/EHiCalculating to obtain heterogeneous cost-to-efficiency ratio Hpro of heterogeneous server softwarei。
And the evaluation module 406 is configured to obtain an evaluation result of the feasibility of the heterogeneous compiling algorithm based on the heterogeneous cost-to-efficiency ratio.
According to the loss of performance value PsriAnd isomeric EHiThe value-taking state of the server software and the heterogeneous cost-effectiveness ratio of the server software are in three extreme states. When Psr isi0 but EHiWhen not equal to 0, HproiWhen the value is 0, the electrode is called as a positive electrode state; when Psr isiNot equal to 0 but EHiWhen 0, Hproi→ infinity, the present invention is referred to as the negative state; when Psr isi0 but EHiWhen 0, the present invention is referred to as the invalid state.
When the heterogeneous cost-to-efficiency ratio is in a positive state, the compiling algorithm corresponding to the heterogeneous server software can generate extremely high benefit in practical application, and is more suitable for generating the heterogeneous executors in the pseudo-structured web server. When the heterogeneous cost-effectiveness ratio is in a negative state, the compiling algorithm corresponding to the heterogeneous server software is extremely low in benefit in practical application, and is not suitable for generating the heterogeneous executors in the pseudo-structure web server. Furthermore, when constructing heterogeneous web service executors, the corresponding compilation algorithm between the positive state and the invalid state should be biased.
In addition, for two heterogeneous server software EiAnd EjIf the precondition Psr is presenti＝PsrjThen HproiAnd HprojThe greater the phase difference, the more heterogeneous server software EiAnd EjThe greater the isomerism between. At this time, pairThe two compilation algorithms should be better suited to construct heterogeneous web service executives for different pools of executives.
In a specific application, the method divides different stages according to the heterogeneous cost-to-efficiency ratio of heterogeneous software. When the heterogeneous cost-to-efficiency ratio value is within the range of 0-2, the heterogeneous server software is considered to be in a normal state, and the corresponding diversified compiling algorithm can be used for constructing a heterogeneous web service execution body; when the heterogeneous cost-to-efficiency ratio value is within the range of 2-4, the heterogeneous server software is considered to be in an unstable state; when the heterogeneous cost-to-efficiency ratio value is more than 4, the heterogeneous server software is considered to be in an unavailable state, the corresponding diversified compiling algorithm cannot be used for constructing a heterogeneous web service execution body, the performance of the web server with a mimicry structure can be seriously influenced, meanwhile, response overtime can cause more false alarms to be generated by the system, and certain interference is caused to a voting mechanism of the system.
In summary, the heterogeneous cost-effectiveness ratio of the compiling algorithm is calculated by quantifying the heterogeneous performance loss value and the performance loss value of the compiled software, and finally the calculation formula of the heterogeneous cost-effectiveness ratio is provided, so that the actual benefit generated by the diversified compiling strategy can be intuitively evaluated, and meanwhile, the method has certain universality, not only can be applied to a pseudo-structured web server, but also can be applied to other safety systems with heterogeneous redundancy characteristics.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A heterogeneous compilation algorithm feasibility assessment method is characterized by comprising the following steps:
determining the heterogeneity of heterogeneous server software;
determining a performance loss value of the heterogeneous server software;
calculating the heterogeneous cost-efficiency ratio of the heterogeneous server software based on the ratio of the performance loss value to the heterogeneity;
and obtaining the evaluation result of the feasibility of the heterogeneous compiling algorithm based on the heterogeneous cost-to-efficiency ratio.
2. The method of claim 1, wherein determining the heterogeneity of heterogeneous server software comprises:
calculating the complexity of the heterogeneous server software;
calculating the difference of the heterogeneous server software;
according to the formula
Calculating the heterogeneity of the heterogeneous server software, wherein EHiRepresenting heterogeneous Server software EiIs the isomerism of EC0Indicating non-heterogeneous server software E0Complexity, EC ofiRepresenting heterogeneous Server software EiComplexity of, EDiRepresenting heterogeneous Server software EiAnd non-heterogeneous Server software E0The difference in the ratio of (a) to (b).
3. The method of claim 2, wherein calculating the complexity of the heterogeneous server software comprises:
constructing complexity index vectors
Wherein C isi＝(ci1，ci2...，cim) Representing heterogeneous Server software EiComplexity index vector of (1), C0Indicating non-heterogeneous server software E0A complexity index vector of;
performing principal component analysis on the complexity index to obtain the calculation weight of each complexity index
According to the formula
Calculating to obtain heterogeneous server software EiThe complexity of (a).
4. The method of claim 3, wherein computing the variability of the heterogeneous server software comprises:
computing heterogeneous servicesSoftware of device EiAnd non-heterogeneous Server software E0Inter-compilation algorithm variability Edai；
For heterogeneous server software EiAnd non-heterogeneous Server software E0The binary files are evaluated differently to obtain an evaluation result Edbi；
According to the formula EDi＝μ1·Edai+μ2·EdbiThe method adopts a weighting calculation mode to carry out weighting calculation on the heterogeneous server software EiAnd non-heterogeneous Server software E0The differences are quantified to obtain the differences ED of the heterogeneous server softwareiWherein, mu1And mu2Is the set weight.
5. The method of claim 4, wherein determining the performance loss value for the heterogeneous server software comprises:
according to the formula
Quantifying the performance loss value of the heterogeneous server software by adopting the standardized Euclidean distance to obtain the performance loss value of the heterogeneous server software, wherein the PsriIs a heterogeneous server software EiThe value of the loss of performance of (c),
is a performance feature vector ViAnd B0Standard deviation between attribute eigenvalues, Vi＝(vi1,vi2,...,vip) Representing heterogeneous Server software EiPerformance feature vector of, B0＝(b1,b2,...bp) Indicating non-heterogeneous server software E0The performance characteristic vector of (2) is used as a reference for calculating the performance loss value of the heterogeneous software.
6. A heterogeneous compilation algorithm feasibility assessment system, comprising:
the first determining module is used for determining the heterogeneity of the heterogeneous server software;
the second determining module is used for determining the performance loss value of the heterogeneous server software;
the calculation module is used for calculating the heterogeneous cost-efficiency ratio of the heterogeneous server software based on the ratio of the performance loss value to the heterogeneity;
and the evaluation module is used for obtaining the evaluation result of the feasibility of the heterogeneous compiling algorithm based on the heterogeneous cost-to-efficiency ratio.
7. The system of claim 6, wherein the first determining module comprises:
the first computing unit is used for computing the complexity of the heterogeneous server software;
the second calculation unit is used for calculating the difference of the heterogeneous server software;
a third calculation unit for calculating
Calculating the heterogeneity of the heterogeneous server software, wherein EHiRepresenting heterogeneous Server software EiIs the isomerism of EC0Indicating non-heterogeneous server software E0Complexity, EC ofiRepresenting heterogeneous Server software EiComplexity of, EDiRepresenting heterogeneous Server software EiAnd non-heterogeneous Server software E0The difference in the ratio of (a) to (b).
8. The system of claim 7, wherein the first computing unit is specifically configured to:
constructing complexity index vectors
Wherein C isi＝(ci1，ci2...，cim) Representing heterogeneous Server software EiComplexity index vector of (1), C0Indicating non-heterogeneous server software E0A complexity index vector of;
performing principal component analysis on the complexity index to obtain the calculation weight of each complexity index
According to the formula
Calculating to obtain heterogeneous server software EiThe complexity of (a).
9. The system of claim 8, wherein the second computing unit is specifically configured to:
compute heterogeneous Server software EiAnd non-heterogeneous Server software E0Inter-compilation algorithm variability Edai；
For heterogeneous server software EiAnd non-heterogeneous Server software E0The binary files are evaluated differently to obtain an evaluation result Edbi；
According to the formula EDi＝μ1·Edai+μ2·EdbiThe method adopts a weighting calculation mode to carry out weighting calculation on the heterogeneous server software EiAnd non-heterogeneous Server software E0The differences are quantified to obtain the differences ED of the heterogeneous server softwareiWherein, mu1And mu2Is the set weight.
10. The system of claim 9, wherein the second determination module is specifically configured to:
according to the formula
Quantifying the performance loss value of the heterogeneous server software by adopting the standardized Euclidean distance to obtain the performance loss value of the heterogeneous server software, wherein the PsriIs a heterogeneous server software EiThe value of the loss of performance of (c),
is a performance feature vector ViAnd B0Standard deviation between attribute eigenvalues, Vi＝(vi1，vi2，...，vip) Representing heterogeneous Server software EiPerformance feature vector of, B0＝(b1，b2，...bp) Indicating non-heterogeneous server software E0The performance characteristic vector of (2) is used as a reference for calculating the performance loss value of the heterogeneous software.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010284688.6A CN111459832B (en) | 2020-04-13 | 2020-04-13 | Heterogeneous compilation algorithm feasibility evaluation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010284688.6A CN111459832B (en) | 2020-04-13 | 2020-04-13 | Heterogeneous compilation algorithm feasibility evaluation method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111459832A true CN111459832A (en) | 2020-07-28 |
| CN111459832B CN111459832B (en) | 2022-09-09 |
Family
ID=71680253
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010284688.6A Active CN111459832B (en) | 2020-04-13 | 2020-04-13 | Heterogeneous compilation algorithm feasibility evaluation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111459832B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112181433A (en) * | 2020-10-16 | 2021-01-05 | 华东计算技术研究所（中国电子科技集团公司第三十二研究所） | Method and system for compiling, running and managing mimic multimode mixed execution body |
| CN115309402A (en) * | 2022-07-13 | 2022-11-08 | 国网江苏省电力有限公司信息通信分公司 | Method and device for forming heterogeneous execution sequence set capable of quantifying differences |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101441569A (en) * | 2008-11-24 | 2009-05-27 | 中国人民解放军信息工程大学 | Novel service flow-oriented compiling method based on heterogeneous reconfigurable architecture |
| WO2015143641A1 (en) * | 2014-03-26 | 2015-10-01 | Empire Technology Development Llc | Compilation of application into multiple instruction sets for a heterogeneous processor |
| CN107145376A (en) * | 2016-03-01 | 2017-09-08 | 中兴通讯股份有限公司 | A kind of active defense method and device |
| CN109218322A (en) * | 2018-09-28 | 2019-01-15 | 郑州昂视信息科技有限公司 | A kind of mimicry defence method, apparatus and system |
| CN109344612A (en) * | 2018-09-25 | 2019-02-15 | 郑州昂视信息科技有限公司 | The active defense method and system inversely attacked for program code static analysis |
-
2020
- 2020-04-13 CN CN202010284688.6A patent/CN111459832B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101441569A (en) * | 2008-11-24 | 2009-05-27 | 中国人民解放军信息工程大学 | Novel service flow-oriented compiling method based on heterogeneous reconfigurable architecture |
| WO2015143641A1 (en) * | 2014-03-26 | 2015-10-01 | Empire Technology Development Llc | Compilation of application into multiple instruction sets for a heterogeneous processor |
| CN107145376A (en) * | 2016-03-01 | 2017-09-08 | 中兴通讯股份有限公司 | A kind of active defense method and device |
| CN109344612A (en) * | 2018-09-25 | 2019-02-15 | 郑州昂视信息科技有限公司 | The active defense method and system inversely attacked for program code static analysis |
| CN109218322A (en) * | 2018-09-28 | 2019-01-15 | 郑州昂视信息科技有限公司 | A kind of mimicry defence method, apparatus and system |
Non-Patent Citations (3)
| Title |
|---|
| MARIA XEKALAKI: "Challenges and Proposals for Enabling Dynamic Heterogeneous Execution of Big Data Frameworks", 《2018 IEEE INTERNATIONAL CONFERENCE ON CLOUD COMPUTING TECHNOLOGY AND SCIENCE (CLOUDCOM)》 * |
| 张宇嘉等: "基于软件多样化的拟态安全防御策略", 《计算机科学》 * |
| 李卫超等: "基于拟态防御架构的多余度裁决建模与风险分析", 《信息安全学报》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112181433A (en) * | 2020-10-16 | 2021-01-05 | 华东计算技术研究所（中国电子科技集团公司第三十二研究所） | Method and system for compiling, running and managing mimic multimode mixed execution body |
| CN112181433B (en) * | 2020-10-16 | 2023-09-26 | 华东计算技术研究所（中国电子科技集团公司第三十二研究所） | Compiling, running and managing method and system of mimicry multimode mixed execution body |
| CN115309402A (en) * | 2022-07-13 | 2022-11-08 | 国网江苏省电力有限公司信息通信分公司 | Method and device for forming heterogeneous execution sequence set capable of quantifying differences |
| CN115309402B (en) * | 2022-07-13 | 2023-10-24 | 国网江苏省电力有限公司信息通信分公司 | Heterogeneous execution program set forming method and device capable of quantifying difference |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111459832B (en) | 2022-09-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111459832B (en) | Heterogeneous compilation algorithm feasibility evaluation method and system | |
| WO2019179248A1 (en) | Anomaly detection method and device | |
| US8935258B2 (en) | Identification of sample data items for re-judging | |
| US8516499B2 (en) | Assistance in performing action responsive to detected event | |
| US20090049549A1 (en) | Apparatus and method for detection of malicious program using program behavior | |
| CN110633222A (en) | Method and device for determining regression test case | |
| CN112600919B (en) | Equipment computing power evaluation method and system based on PoW consensus mechanism | |
| CN112785157A (en) | Risk identification system updating method and device and risk identification method and device | |
| US20230038579A1 (en) | Classification model training method, system, electronic device and strorage medium | |
| CN111581036A (en) | Internet of things fault detection method, detection system and storage medium | |
| KR20090005934A (en) | Apparatus and method for detection of malicious program using program behavior | |
| CN111897696A (en) | Server cluster hard disk state detection method and device, electronic equipment and storage medium | |
| CN111639722A (en) | Transformer fault diagnosis method based on principal component analysis and twin support vector machine | |
| CN115766169A (en) | Malicious node detection method in federated learning | |
| CN111752481A (en) | Memory monitoring and service life prediction method and system based on SPD | |
| CN113537614A (en) | Construction method, system, equipment and medium of power grid engineering cost prediction model | |
| CN115577312B (en) | Building electricity load curve anomaly detection method based on improved DAGMM | |
| CN113220552B (en) | Method and electronic equipment for limiting application operation number in vehicle-mounted information entertainment system | |
| CN113344246B (en) | Nuclear power plant supervision requirement optimization method | |
| CN112416709B (en) | Chip dynamic power consumption estimation method and device, processor chip and server | |
| CN114499408A (en) | Information testing method and system based on battery big data | |
| CN110472191B (en) | Dynamic self-adaptive service evaluation calculation method and device | |
| CN110704461A (en) | Data verification method and device, computer equipment and readable storage medium | |
| CN111309716A (en) | Maintenance method and device applied to PAS case base and computer equipment | |
| CN111310177A (en) | Video monitoring equipment attack detection system based on memory behavior characteristics |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |