CN112969180B - Wireless sensor network attack defense method and system in fuzzy environment - Google Patents
Wireless sensor network attack defense method and system in fuzzy environment Download PDFInfo
- Publication number
- CN112969180B CN112969180B CN202110349414.5A CN202110349414A CN112969180B CN 112969180 B CN112969180 B CN 112969180B CN 202110349414 A CN202110349414 A CN 202110349414A CN 112969180 B CN112969180 B CN 112969180B
- Authority
- CN
- China
- Prior art keywords
- wireless sensor
- sensor network
- fuzzy
- defense
- attack
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
- G06N5/042—Backward inferencing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W84/00—Network topologies
- H04W84/18—Self-organising networks, e.g. ad-hoc networks or sensor networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computer And Data Communications (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a wireless sensor network attack defense method under a fuzzy environment, which adopts an intrusion detection system to detect the attack of a malicious program, obtains the income obtained by the malicious program, the loss of a wireless sensor network, the defense cost of the wireless sensor network and the infection cost of the malicious program based on the detection data of the intrusion detection system, defines the variables as fuzzy variables, introduces the environmental confidence and the decision angle, constructs a wireless sensor network attack and defense game model, solves the wireless sensor network attack and defense game model based on a Stackelberg game method and a fuzzy set theory to obtain the Nash equilibrium solution of the wireless sensor network and the malicious program attack and defense game in the fuzzy environment, expands the non-fuzzy wireless sensor network attack and defense game to an uncertain condition to specifically analyze the optimal strategy adopted by the wireless sensor network in the fuzzy environment, the decision-making capability and the capability of defending against malicious program attacks of the wireless sensor network in a fuzzy environment can be improved.
Description
Technical Field
The invention belongs to the technical field of network security, and particularly relates to a method and a system for defending a wireless sensor network attack in a fuzzy environment.
Background
A Wireless Sensor Network (WSN) is a network composed of a plurality of sensor nodes having a certain topology. The WSN is an ad-hoc wireless network that collects information through each sensor node and ultimately aggregates it to a target node for analysis. Currently, WSNs have been widely used in the fields of environmental management, pollution control, industrial production, and medical application in the real world. With the wide application of the WSN, some problems encountered in the WSN application process also occur. For example, in reality, WSNs are often attacked by malicious programs. The attack of a malicious program can cause the problems of data loss, rapid energy loss and the like of the WSN. Therefore, improving the ability of the WSN to defend against malicious program attacks has become an important research direction for increasing the security performance of the WSN.
The game theory is a method theory for researching the strategy established by a plurality of participants when the participants play the fighting or cooperative behaviors based on the limited conditions. The attack and defensive behavior between malicious programs and WSNs allows both parties to be considered two participants in the game. One method that is commonly used today is to model the defense and attack process that occurs between malicious programs and the WSN using a classical game model. Specifically, the method defines various variables influencing profits of two participants in the process of attacking and defending the WSN and the malicious program, then uses the defined variables to formulate a benefit formula of the malicious program and the WSN, and finally uses a game evolution method to obtain a Nash equilibrium solution of the malicious program and the WSN in the process of attacking and defending, and the method for obtaining the WSN optimal defense strategy by using the game theory effectively improves the security performance of the WSN.
The inventor finds in research that in reality, the ambiguity of information may cause cognitive uncertainty in the defense and attack process of the WSN and malicious programs, specifically: in the prior art, damage caused by data loss to the WSN and the benefit of malicious software cannot be accurately evaluated, so that ambiguity exists in evaluation of data loss of nodes, and further uncertainty of attack strategies and defense strategies is caused. The existence of cognitive uncertainty greatly limits the non-fuzzy game model which is commonly used for analyzing WSN defense strategies at present in the analysis process.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a wireless sensor network attack defense method in a fuzzy environment, and the optimal strategy which can be adopted by the WSN in the fuzzy environment is specifically analyzed by expanding the non-fuzzy WSN attack defense game to an uncertain condition, so that the decision-making capability of the WSN in the fuzzy environment and the capability of defending malicious program attack can be improved.
To achieve the above object, one or more embodiments of the present invention provide the following solutions:
the wireless sensor network attack defense method under the fuzzy environment comprises the following steps:
detecting attacks of malicious programs by adopting an intrusion detection system;
based on the detection data of an intrusion detection system, obtaining the income obtained by a malicious program, the loss of a wireless sensor network, the defense cost of the wireless sensor network and the infection cost of the malicious program, defining the variables as fuzzy variables, introducing environmental confidence and decision angle, and constructing a WSN attack and defense game model;
and solving the WSN attack and defense game model based on a Stackelberg game method and a fuzzy set theory to obtain Nash equilibrium solution of the attack and defense game of the wireless sensor network and the malicious program in the fuzzy environment.
In a further technical scheme, the detecting the attack of the malicious software by using the intrusion detection system specifically comprises:
based on the probability of successfully detecting the attack of the malicious software by the intrusion detection system and the false alarm rate of the intrusion detection system, the malicious software obtains partial data of the wireless sensor network node after the malicious software successfully infects the wireless sensor network node, namely the income obtained by the malicious software.
For the wireless sensor network, after the node is infected, the wireless sensor network loses the corresponding node data, i.e. the loss of the wireless sensor network.
When the wireless sensor network defends infection, the wireless sensor network pays a certain amount of energy to support the operation of a defense system, namely the defense cost of the wireless sensor network, and for malicious software, the energy paid by infecting a node is expressed as the infection cost of the malicious software.
In a further technical scheme, the introducing of the environment confidence and the decision angle to construct the WSN attacking and defending game model comprises the following steps:
assuming that the attack and defense processes of the WSN and the malicious program are in a fuzzy environment;
constructing profits of the malicious program and the WSN;
and modeling the WSN attack and defense game in the fuzzy environment based on the opportunity constraint model.
According to the further technical scheme, the environment confidence degrees are the environment confidence degree of the malicious program and the environment confidence degree of the WSN, and the decision angles are an optimistic decision angle and a pessimistic decision angle.
According to the further technical scheme, the opportunity constraint model is a multi-level uncertain opportunity constraint model and comprises a max i max and min i max opportunity constraint model, and an optimistic decision angle and a pessimistic decision angle of the WSN and the malicious program are represented based on the max i max and min i max opportunity constraint model.
In a further technical scheme, the establishment of the WSN attack and defense game opportunity constraint model from an optimistic decision angle based on the max i max opportunity constraint is as follows:
where α is the malware's environmental confidence, e is the WSN's environmental confidence, s.t is a notation that indicates "restricted," Pos {. is the likelihood of occurrence of the thing, U is a notation that indicates the optimistic value of the fuzzy variable, in the max i max chance constraint model, the WSN and malware aim to maximize the optimistic value of the revenue.
According to the further technical scheme, the WSN attack and defense game model is solved based on the Stackelberg game method and the fuzzy set theory, and the method specifically comprises the following steps:
expanding an optimistic value of profit of the malicious program in the fuzzy environment based on the confidence coefficient alpha and an optimistic value of profit of the WSN in the fuzzy environment based on the confidence coefficient epsilon by using fuzzy set theory;
deducing a first derivative and a second derivative of strategies of the WSN and malicious programs in the game based on a Stackelberg game theory to obtain a Nash equilibrium solution of the WSN attack and defense game model;
and formulating a corresponding optimal defense strategy based on the Nash equilibrium solution.
The implementation mode of the description provides a wireless sensor network attack defense method in a fuzzy environment, which is realized by the following technical scheme:
the method comprises the following steps:
an attack detection module, the benefit configured to: detecting attacks of malicious programs by adopting an intrusion detection system;
an attack and defense game building module configured to: based on the detection data of an intrusion detection system, obtaining the income obtained by a malicious program, the loss of a wireless sensor network, the defense cost of the wireless sensor network and the infection cost of the malicious program, defining the variables as fuzzy variables, introducing environmental confidence and decision angle, and constructing a WSN attack and defense game model;
a defense policy making module configured to: and solving the WSN attack and defense game model based on a Stackelberg game method and a fuzzy set theory to obtain Nash equilibrium solution of the attack and defense game of the wireless sensor network and the malicious program in the fuzzy environment.
Compared with the prior art, the beneficial effect of this disclosure is:
(1) according to the method and the device, the malicious software attack is detected, the loss of data loss to the wireless sensor network and the benefit of malicious software can be accurately evaluated, and the protection probability meeting the fuzzy information condition is set for each node on the wireless sensor network so that the loss of the whole wireless sensor network is minimum under the malicious software attack.
(2) The analysis model provided by the disclosure can analyze and determine the optimal strategy of the WSN and the malicious software attacking and defending game in the environment, and can also analyze the optimal strategy of the WSN and the malicious software in the fuzzy environment.
(3) The max i max chance constraint model and the min i max chance constraint model which are established based on the WSN attack and defense game can compare the influence degree of external and internal factors on the WSN.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure and are not to limit the disclosure.
FIG. 1 is a schematic flow chart of a wireless sensor network attack defense method in a fuzzy environment according to an embodiment of the present disclosure;
FIG. 2a is a diagram illustrating the impact of a disclosed existing model on the optimal defense strategy of a WSN, according to an embodiment of the present disclosure;
FIG. 2b is a diagram illustrating the impact of the best defense strategy for the optimizers decision-making angle WSN according to an embodiment of the present invention;
FIG. 2c is a diagram illustrating the impact of the best defense strategy for a pessimistic decision angle WSN according to an embodiment of the present invention.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present disclosure. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
The embodiments and features of the embodiments of the present invention may be combined with each other without conflict.
The invention has the overall concept that:
the method comprises the steps of evaluating loss of data to a wireless sensor network and benefits of malicious software, modeling an original WSN attack and defense game by adopting a multilayer uncertain chance constraint model in fuzzy analysis, introducing two influence factors of environment confidence and decision angle for the WSN attack and defense game in a fuzzy environment by using a max i max chance constraint model and a min i max chance constraint model in the multilayer uncertain chance constraint model, solving the formulated model by using a Stackelberg game method and a fuzzy set theory, and finally obtaining a Nash equilibrium solution of the WSN attack and defense game in the fuzzy environment.
Example of implementation 1
The embodiment discloses a method for defending wireless sensor network attacks in a fuzzy environment, and aims to: the optimal attack and defense strategies of the WSN and the malicious software are analyzed through the fuzzy external environment.
Description of the parameters:
TABLE 1 Game parameters
As shown in fig. 1, the present application provides a method for defending against a wireless sensor network attack in a fuzzy environment, which includes the following steps:
step 1: detecting attacks of malicious programs by adopting an Intrusion Detection System (IDS);
the probability of successful detection of a malware attack by the IDS is denoted as γ, while the false alarm rate of the IDS is denoted as β. After the WSN node is successfully infected by the malicious program, the malicious program can obtain partial data of the WSN node, namely the income obtained by the malicious program
For the WSN, when the node is infected, the WSN loses the corresponding node data, which is expressed as the loss of the WSN
The damage caused to the WSN and the benefits of malware due to the loss of data cannot be accurately assessed. Thus, the evaluation of node missing data contains ambiguity. In terms of defense against infection, WSN requires a certain amount of energy to support the operation of defense system, which is expressed as defense cost of WSN
For malware, the energy paid to infect a node is represented as the infection cost of the malware
Step 2: based on the detection data of an intrusion detection system, obtaining the income obtained by a malicious program, the loss of a wireless sensor network, the defense cost of the wireless sensor network and the infection cost of the malicious program, defining the variables as fuzzy variables, introducing environmental confidence and decision angle, and constructing a WSN attack and defense game model;
the method comprises the following steps:
step 201: assuming that the attack and defense processes of the WSN and the malicious program are in a fuzzy environment;
there is uncertainty in the cost of WSNs and malicious programs due to the problem of hardware failures in WSN networks. The existence of the uncertainty causes uncertainty in the attack and defense game of the WSN and the malicious program. Therefore, the four parameters are combined
Set as the fuzzy variable.
Step 202: revenue for building malicious programs and WSNs is expressed as follows:
wherein the content of the first and second substances,
for the benefit of malicious programs in a fuzzy environment,
for the benefit of the WSN in the fuzzy environment, p and q respectively represent the strategies of a malicious program and the WSN in the game, gamma is the probability of successfully detecting the malicious program by the intrusion detection system, lambda is the probability of successfully infecting WSN nodes when the malicious program is not defended or detected by the WSN, beta is the false alarm rate of the intrusion detection system (namely the intrusion detection system detects the malicious program but does not actually have the malicious program),
utility, omega, of malware successfully infecting nodes in a fuzzy environmentDIn order to realize the purpose,
is at the same timeWSNs in obscured environments are lost due to successful infection by malware or false alarms,
for the infection cost of malicious programs in a fuzzy environment,
is the defense cost of the WSN in a fuzzy environment.
Step 203: modeling the WSN attack and defense game in the fuzzy environment based on the opportunity constraint model;
the environment confidence coefficient is an environment confidence coefficient of a malicious program and an environment confidence coefficient of the WSN, and the decision angle is an optimistic decision angle and a pessimistic decision angle;
expressing an optimistic decision angle and a pessimistic decision angle of the WSN and the malicious program by using a max i max and min i max opportunity constraint model in a multilayer uncertain opportunity constraint model;
(1) in an optimistic decision angle of the WSN and a malicious program, in a fuzzy environment, a max i max chance constraint model based on the WSN attack and defense game is constructed as follows:
in the max opportunity constraint model, the WSN and the malware aim to maximize the optimistic value of revenue, and alpha and the epsilon in the model respectively represent the confidence degrees of the malware and the WSN to the current game environment.
(2) In a fuzzy environment, a min i max chance constraint model based on a WSN attack and defense game is constructed from a pessimistic decision angle of the WSN and a malicious program as follows:
in the min i max chance constraint model, the malicious program and the WSN aim at maximizing the pessimistic value of the self income, and in addition, the WSN and the malicious program in the model also have different environment confidence degrees.
The established max i max and min i max opportunity constraint models represent optimistic and pessimistic decision angles of the WSN and the malicious program respectively.
And 3, step 3: and solving the WSN attack and defense game model based on a Stackelberg game method and a fuzzy set theory to obtain Nash equilibrium solution of the attack and defense game of the wireless sensor network and the malicious program in the fuzzy environment.
In this embodiment, the solving process of the max i max chance constraint model based on the WSN attack and defense game is as follows:
first, using fuzzy set theory to extend
And
the following were used:
wherein the content of the first and second substances,
an optimistic value representing the benefit of a malware in a fuzzy environment based on the confidence level alpha,
representing an optimistic value of WSN income in the fuzzy environment based on the confidence coefficient E;
then, based on the Stackelberg game theory, deducing
The first and second derivatives with respect to q are as follows:
it is clear that,
is a strictly convex function. Therefore, the optimal strategy for a WSN based on the revenue optimistic value is:
optimal strategy q to be based on revenue optimistic value*(p) substitution into extended formula
In (1), also according to the Stackelberg game theory,
the first and second derivatives for p are calculated as follows:
it is clear that,
is also a strictly convex function. Thus, the optimal policy for malicious programs based on the optimistic value of revenue is:
the solution process of the min i max opportunity constraint model based on the WSN attack and defense game is similar to that of the max i max opportunity constraint model in the first embodiment, and details are not repeated here.
And (4) combining the WSN and an opportunity constraint model of the malicious program to obtain a Nash equilibrium solution and formulating a corresponding optimal defense strategy.
Optimal strategy for integrating malicious programs and WSNs to obtain Nash equilibrium solution (p) of max i max opportunity constraint model*,q*(p*) Obtaining Nash equilibrium solution of the WSN and malicious program attacking and defending game in the fuzzy environment;
based on Nash equilibrium solutions of the max i max and min i max chance constraint models, the WSN can work out corresponding optimal defense strategies according to different fuzzy environments (environmental confidence degrees of the WSN and the malicious programs).
In order to make the technical solutions of the present disclosure more clearly understood by those skilled in the art, the technical solutions of the present disclosure will be described in detail below with reference to specific examples and comparative examples.
In this embodiment, compared with the existing method, the influence of the environmental confidence on the WSN optimal defense strategy is considered in the present disclosure, as shown in fig. 2a, it is shown that the existing model cannot analyze the influence of the environmental confidence on the WSN optimal defense strategy; as shown in fig. 2b, it is shown that the method of the present disclosure can analyze the influence of environment confidence on the best defense strategy of the WSN, and therefore, the existing method for analyzing the WSN attack and defense game in the fuzzy environment may cause the strategy formulated by the WSN not to be the best strategy in the current environment. In addition, the method of the present disclosure also considers the influence of the decision angle on the optimal defense strategy of the WSN, and as shown in fig. 2c, the change of the optimal defense strategy of the WSN under the optimistic decision angle and the pessimistic decision angle is shown respectively.
From the above description, it can be seen that the above-described embodiments of the present application achieve the following technical effects:
(1) the method specifically analyzes the optimal strategy adopted by the WSN in the fuzzy environment by expanding the non-fuzzy WSN attack and defense game to an uncertain condition, so that the decision-making capability of the WSN in the fuzzy environment and the capability of defending malicious program attacks can be improved.
(2) The method analyzes two viewpoints of decision-making of the WSN and malicious software in a fuzzy environment respectively, namely an optimistic value and a pessimistic value of maximized income, uses simulation data to prove the influence of confidence level and decision viewpoint on game decision-making and reliability of the WSN, compares non-fuzzy WSN attack and defense game methods, and is excellent in behavior of resisting malicious software attack.
Example II
The implementation mode of the description provides a wireless sensor network attack defense strategy analysis system in a fuzzy environment, and the method is realized by the following technical scheme:
the method comprises the following steps:
an attack detection module, the benefit configured to: detecting attacks of malicious programs by adopting an intrusion detection system;
an attack and defense game building module configured to: based on the detection data of an intrusion detection system, obtaining income obtained by a malicious program, loss of a wireless sensor network, defense cost of the wireless sensor network and infection cost of the malicious program, defining the variables as fuzzy variables, introducing environment confidence and decision angle, and constructing a WSN attack and defense game model;
a defense policy making module configured to: and solving the WSN attacking and defending game model based on a Stackelberg game method and a fuzzy set theory to obtain a Nash equilibrium solution of the attacking and defending game of the wireless sensor network and the malicious program in the fuzzy environment.
The implementation of the specific modules in this embodiment example can be referred to in the related art in the first embodiment example, and will not be described in detail here.
Example III
The computer device comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, and is characterized in that the processor executes the program to implement the steps of the method for analyzing the attack defense strategy of the wireless sensor network in the fuzzy environment in the first embodiment.
Example four
The embodiment of the present specification provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the steps of implementing the method for analyzing attack defense policy of wireless sensor network in fuzzy environment in the first example.
It is to be understood that throughout the description of the present specification, reference to the term "one embodiment", "another embodiment", "other embodiments", or "first through nth embodiments", etc., is intended to mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, or materials described may be combined in any suitable manner in any one or more embodiments or examples.
The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure, and various modifications and changes may be made to the present disclosure by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.
Claims (6)
1. The method for defending the attack of the wireless sensor network in the fuzzy environment is characterized by comprising the following steps:
detecting attacks of malicious programs by adopting an intrusion detection system;
based on the detection data of an intrusion detection system, the income obtained by a malicious program, the loss of a wireless sensor network, the defense cost of the wireless sensor network and the infection cost of the malicious program are obtained, the variables are defined as fuzzy variables, the environmental confidence and the decision angle are introduced, and a wireless sensor network attack and defense game model is constructed, which specifically comprises the following steps:
respectively constructing malicious programs and benefits of a wireless sensor network in a fuzzy environment based on fuzzy variables
And
the method for representing the optimistic decision angle and the pessimistic decision angle of the malicious program and the wireless sensor network by using the max i max and min i max opportunity constraint models in the multilayer uncertain opportunity constraint model specifically comprises the following steps:
from an optimistic decision perspective, a max i max chance constraint model based on the WSN attack and defense game is constructed as follows:
in the max imax chance constraint model, the WSN and the malware aim to maximize the optimistic value of income, Pos {. is the probability of occurrence of things, and p and q respectively represent the strategies of the malware and the WSN in the game;
from the perspective of pessimistic decision, a min i max chance constraint model based on the WSN attack and defense game is constructed as follows:
wherein L is a symbol representing a pessimistic value of a fuzzy variable, and in the min i max chance constraint model, the malicious program and the WSN aim to maximize the pessimistic value of the self income;
solving the wireless sensor network attack and defense game model based on the Stackelberg game method and the fuzzy set theory to obtain Nash equilibrium solution of the wireless sensor network and the malicious program attack and defense game in the fuzzy environment.
2. The method for defending against attacks by a wireless sensor network in a fuzzy environment according to claim 1, wherein said detecting attacks by malicious programs by using an intrusion detection system comprises:
based on the probability of successfully detecting the attack of the malicious program by the intrusion detection system and the false alarm rate of the intrusion detection system, partial data of the wireless sensor network node, namely the income obtained by the malicious program, is obtained by the malicious program after the wireless sensor network node is successfully infected by the malicious program, for the wireless sensor network, after the node is infected, the wireless sensor network loses the corresponding node data, namely the loss of the wireless sensor network, and when the wireless sensor network defends infection, the wireless sensor network pays certain energy to support the operation of the defense system, namely the defense cost of the wireless sensor network, and for the malicious software, the energy paid by infecting one node, namely the infection cost of the malicious program.
3. The method for defending wireless sensor network attack in the fuzzy environment as claimed in claim 1, wherein the wireless sensor network attack and defense game model is solved based on the Stackelberg game method and the fuzzy set theory, and specifically comprises the following steps:
expanding the gain of the malicious program in the fuzzy environment based on the optimistic value and the pessimistic value of the confidence coefficient alpha by using fuzzy set theory, and expanding the gain of the wireless sensor network in the fuzzy environment based on the optimistic value and the pessimistic value of the confidence coefficient epsilon;
deducing a first derivative and a second derivative of strategies of the wireless sensor network and malicious programs in the game based on the Stackelberg game theory to obtain a Nash equilibrium solution of a wireless sensor network attack and defense game model;
and formulating a corresponding optimal defense strategy based on the Nash equilibrium solution.
4. The wireless sensor network attack defense system under the fuzzy environment is characterized by comprising:
an attack detection module, the avails configured to: detecting attacks of malicious programs by adopting an intrusion detection system;
an attack and defense game building module configured to: based on the detection data of an intrusion detection system, the income obtained by a malicious program, the loss of a wireless sensor network, the defense cost of the wireless sensor network and the infection cost of the malicious program are obtained, the variables are defined as fuzzy variables, the environmental confidence and the decision angle are introduced, and a wireless sensor network attack and defense game model is constructed, which comprises the following steps:
respectively constructing malicious programs and benefits of a wireless sensor network in a fuzzy environment based on fuzzy variables
And
the method for representing the optimistic decision angle and the pessimistic decision angle of the malicious program and the wireless sensor network by using the max i max and min i max opportunity constraint models in the multilayer uncertain opportunity constraint model specifically comprises the following steps:
from an optimistic decision perspective, a max i max chance constraint model based on the WSN attack and defense game is constructed as follows:
in the max imax chance constraint model, the WSN and the malware aim to maximize the optimistic value of income, Pos {. is the probability of occurrence of things, and p and q respectively represent the strategies of the malware and the WSN in the game;
from the perspective of pessimistic decision, a min i max chance constraint model based on the WSN attack and defense game is constructed as follows:
wherein L is a symbol representing a pessimistic value of a fuzzy variable, and in the min i max chance constraint model, the malicious program and the WSN aim to maximize the pessimistic value of the self income;
a defense policy making module configured to: solving the wireless sensor network attack and defense game model based on the Stackelberg game method and the fuzzy set theory to obtain Nash equilibrium solution of the wireless sensor network and the malicious program attack and defense game in the fuzzy environment.
5. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the method for defending against wireless sensor network attacks in a fuzzy environment according to any one of claims 1 to 3.
6. A computer-readable storage medium, on which a computer program is stored, wherein the program, when executed by a processor, implements the steps of the method for defending against attacks on a wireless sensor network in a fuzzy environment according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110349414.5A CN112969180B (en) | 2021-03-31 | 2021-03-31 | Wireless sensor network attack defense method and system in fuzzy environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110349414.5A CN112969180B (en) | 2021-03-31 | 2021-03-31 | Wireless sensor network attack defense method and system in fuzzy environment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112969180A CN112969180A (en) | 2021-06-15 |
| CN112969180B true CN112969180B (en) | 2022-07-01 |
Family
ID=76279866
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110349414.5A Active CN112969180B (en) | 2021-03-31 | 2021-03-31 | Wireless sensor network attack defense method and system in fuzzy environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112969180B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117596597B (en) * | 2024-01-18 | 2024-04-12 | 北京邮电大学 | Active defense method and device for DRDoS attack |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106656571A (en) * | 2016-11-09 | 2017-05-10 | 天津大学 | Clustering wireless sensor network malicious program propagation model based on evolution game |
| CN106936855A (en) * | 2017-05-12 | 2017-07-07 | 中国人民解放军信息工程大学 | Network security defence decision-making based on attacking and defending differential game determines method and its device |
| CN108898010A (en) * | 2018-06-25 | 2018-11-27 | 北京计算机技术及应用研究所 | A method of establishing the attacking and defending Stochastic Game Model towards malicious code defending |
| CN110300106A (en) * | 2019-06-24 | 2019-10-01 | 中国人民解放军战略支援部队信息工程大学 | Mobile target based on Markov time game defends decision choosing method, apparatus and system |
| CN111385288A (en) * | 2020-02-20 | 2020-07-07 | 中国人民解放军战略支援部队信息工程大学 | Mobile target defense opportunity selection method and device based on hidden countermeasures |
-
2021
- 2021-03-31 CN CN202110349414.5A patent/CN112969180B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106656571A (en) * | 2016-11-09 | 2017-05-10 | 天津大学 | Clustering wireless sensor network malicious program propagation model based on evolution game |
| CN106936855A (en) * | 2017-05-12 | 2017-07-07 | 中国人民解放军信息工程大学 | Network security defence decision-making based on attacking and defending differential game determines method and its device |
| CN108898010A (en) * | 2018-06-25 | 2018-11-27 | 北京计算机技术及应用研究所 | A method of establishing the attacking and defending Stochastic Game Model towards malicious code defending |
| CN110300106A (en) * | 2019-06-24 | 2019-10-01 | 中国人民解放军战略支援部队信息工程大学 | Mobile target based on Markov time game defends decision choosing method, apparatus and system |
| CN111385288A (en) * | 2020-02-20 | 2020-07-07 | 中国人民解放军战略支援部队信息工程大学 | Mobile target defense opportunity selection method and device based on hidden countermeasures |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112969180A (en) | 2021-06-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Li et al. | LSTM-BA: DDoS detection approach combining LSTM and Bayes | |
| CN105871882B (en) | Network security risk analysis method based on network node fragility and attack information | |
| Wang et al. | Rooting our rumor sources in online social networks: The value of diversity from multiple observations | |
| Abdalzaher et al. | Using Stackelberg game to enhance node protection in WSNs | |
| CN112003854B (en) | Network security dynamic defense decision method based on space-time game | |
| CN114499982A (en) | Honey net dynamic configuration strategy generating method, configuration method and storage medium | |
| CN112969180B (en) | Wireless sensor network attack defense method and system in fuzzy environment | |
| Shen et al. | An epidemiology-based model for disclosing dynamics of malware propagation in heterogeneous and mobile WSNs | |
| Yu | Analyze the worm-based attack in large scale P2P networks | |
| Tan et al. | A survey: When moving target defense meets game theory | |
| Li et al. | Anti-honeypot enabled optimal attack strategy for industrial cyber-physical systems | |
| Shi et al. | A dynamic programming model for internal attack detection in wireless sensor networks | |
| CN110048885B (en) | Effectiveness evaluation method based on virtual triangle in tactical internet | |
| Zheng et al. | Defense technology of wormhole attacks based on node connectivity | |
| Gangula et al. | A comprehence study of DDoS attack detecting algorithm using GRU-BWFA classifier | |
| Lin et al. | Privacy‐Enhanced Intrusion Detection and Defense for Cyber‐Physical Systems: A Deep Reinforcement Learning Approach | |
| Lui et al. | Agent-based network intrusion detection system using data mining approaches | |
| Shen | A game-theoretic approach for optimizing intrusion detection strategy in WSNs | |
| CN112491801B (en) | Incidence matrix-based object-oriented network attack modeling method and device | |
| Guan et al. | A Bayesian Improved Defense Model for Deceptive Attack in Honeypot-Enabled Networks | |
| CN111431865B (en) | Network deep threat detection method | |
| Daund et al. | Intrusion Detection in Wireless Sensor Networks using Hybrid Deep Belief Networks and Harris Hawks Optimizer | |
| Shi et al. | Flocking control for Cucker–Smale model under denial‐of‐service attacks | |
| Yan et al. | An Intelligent Game Theory Framework for Detecting Advanced Persistent Threats | |
| Wang et al. | Simulation of Cloud Computing Network Security Intrusion Detection Model Based on Neural Network Algorithm Driven by Big Data |
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 |