CN113672932A - Electric power Internet of things intelligent terminal trusted computing trust value obtaining method based on self-adaptive entropy value weight - Google Patents

Electric power Internet of things intelligent terminal trusted computing trust value obtaining method based on self-adaptive entropy value weight Download PDF

Info

Publication number
CN113672932A
CN113672932A CN202110823978.8A CN202110823978A CN113672932A CN 113672932 A CN113672932 A CN 113672932A CN 202110823978 A CN202110823978 A CN 202110823978A CN 113672932 A CN113672932 A CN 113672932A
Authority
CN
China
Prior art keywords
trust value
terminal
trust
value
indirect
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.)
Pending
Application number
CN202110823978.8A
Other languages
Chinese (zh)
Inventor
尹喜阳
刘乙召
王忠钰
李达
武云海
李雅君
陆凌辉
张恩杰
张博文
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
State Grid Corp of China SGCC
State Grid Tianjin Electric Power Co Ltd
Information and Telecommunication Branch of State Grid Tianjin Electric Power Co Ltd
Original Assignee
State Grid Corp of China SGCC
State Grid Tianjin Electric Power Co Ltd
Information and Telecommunication Branch of State Grid Tianjin Electric Power Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by State Grid Corp of China SGCC, State Grid Tianjin Electric Power Co Ltd, Information and Telecommunication Branch of State Grid Tianjin Electric Power Co Ltd filed Critical State Grid Corp of China SGCC
Priority to CN202110823978.8A priority Critical patent/CN113672932A/en
Publication of CN113672932A publication Critical patent/CN113672932A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/50—Monitoring users, programs or devices to maintain the integrity of platforms, e.g. of processors, firmware or operating systems
    • G06F21/57—Certifying or maintaining trusted computer platforms, e.g. secure boots or power-downs, version controls, system software checks, secure updates or assessing vulnerabilities
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y40/00—IoT characterised by the purpose of the information processing
    • G16Y40/50—Safety; Security of things, users, data or systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Security & Cryptography (AREA)
  • Computer Hardware Design (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

The invention relates to a self-adaptive entropy weight-based trusted computing trust value acquisition method for an intelligent terminal of an electric power internet of things, which is operated in a distributed mode by an electric power internet of things terminal device based on self-organizing communication connection, fully considers the interaction characteristics of the intelligent terminal of the electric power internet of things in a network and the internal attack characteristics of the network initiated by an untrusted terminal: the method comprises the steps of firstly calculating a direct trust value through a credibility statistical probability model based on beta distribution, then adopting entropy values to construct sub-indirect trust value self-adaptive weights from different recommendation terminals, aiming at the one-sided problem of complete trust value evaluation only consisting of the direct trust value and the indirect trust value, introducing a multi-evaluation-subject comprehensive trust value constructed by the self-adaptive entropy value weights, and improving the identification accuracy. Through experimental data analysis, compared with the existing algorithm, the method has higher accuracy and recall rate under different terminal densities and different malicious node proportions.

Description

Electric power Internet of things intelligent terminal trusted computing trust value obtaining method based on self-adaptive entropy value weight
Technical Field
The invention relates to a trusted computing method for an electric power internet of things terminal, in particular to a trusted computing trust value obtaining method for an electric power internet of things intelligent terminal based on adaptive entropy weight.
Background
The reliability and security issues of the Power Internet of Things (PIoT) become more critical with the development of energy Internet technology and the electricity market. Traditional encryption and authentication schemes are mainly used to defend against external attacks and are not effective against internal attacks initiated by infected devices. Trust management is considered to be an effective way for solving the internal security problem of the power internet of things, however, most of the existing network trust management schemes evaluate objects from the perspective of a certain node, cannot well reflect the overall reputation condition of the objects in the whole network, and have certain one-sidedness. Therefore, how to calculate the trust values of various intelligent terminal devices accessed to the internet of things of the power network in the network, discover and resist the attack behavior from the inside of the network in time, and maintain the security of the PIoT network becomes a problem to be solved urgently.
The method for acquiring the trusted computing trust value of the intelligent terminal provided by the invention constructs the comprehensive trust value of the terminal in the network through the self-adaptive entropy weight according to the interaction characteristics of the terminal in the network and the internal attack characteristics of the network initiated by the untrusted terminal, thereby greatly improving the identification accuracy.
Disclosure of Invention
The invention aims to solve the technical problem of providing a method for acquiring the trusted computing trust value of the intelligent terminal of the power internet of things, which is used for carrying out reasonable credit evaluation according to the historical interaction condition between terminals and improving the identification accuracy of the untrusted terminal which initiates the internal attack of the network.
The technical scheme adopted by the invention is as follows: a method for obtaining a trusted computing trust value of an intelligent terminal of an electric power internet of things based on adaptive entropy weight comprises the following steps:
1) and (3) initializing a trust value: defining a complete trust value obtained by evaluating a terminal j by an intelligent terminal i of the power internet of things as Tij，
Figure BDA0003172961190000011
TijThe closer to 1, the higher the credibility of j is, the trust values of the initial state terminal are all set to 0.5, namely the terminal equipment is considered to be credible to a certain extent;
2) and (3) extracting a trust value parameter: the intelligent terminals in the power Internet of things are interactively cooperated according to application requirements, whether interaction is successful or not is judged by taking the communication channel establishment time t and the communication data quantity q between the terminals as standards, and an interaction result is defined as
Figure BDA0003172961190000012
Cumulative successful interaction times S between terminal i and terminal jijAnd accumulated number of interaction failures FijIn order to calculate parameters required by the trust value, the terminal records the interaction result after each interaction, generates the trust parameters, and then locally stores the trust parameters and continuously updates the trust parameters along with the interaction;
3) direct trust value calculation: evaluation subject terminal iRecording the direct credit evaluation result of the evaluation object terminal j as a direct trust value D according to the historical interaction conditionijThe beta distribution is taken as a credible statistical probability model, and can be well fitted with credible distribution, and the probability density function is as follows:
Figure BDA0003172961190000021
the mathematical expectation of the probability density function is used as a direct trust value of terminal evaluation, and the calculation method comprises the following steps:
Figure BDA0003172961190000022
4) and (3) calculating a sub indirect trust value: the indirect trust value is the indirect trust evaluation of j acquired by i from a recommending terminal x, the recommending terminal x is a terminal which can interact with both i and j, and the sub indirect trust value from the recommending terminal x is calculated:
Figure BDA0003172961190000023
5) and (3) calculating the adaptive weight of the sub indirect trust value: if i evaluates j, n recommendation terminals exist, n sub indirect trust values can be obtained according to the step 4), and the entropy value of each sub indirect trust value is
Figure BDA0003172961190000024
Constructing adaptive weights for the sub-indirect trust values using entropy values:
Figure BDA0003172961190000025
6) and (3) indirect trust value calculation: calculating the indirect trust value of i to j as
Figure BDA0003172961190000026
7) And (3) self-adaptive weight calculation of the direct trust value and the indirect trust value: entropy of the direct trust value obtained according to step 3) is H (D)ij)＝-Dijlog2Dij-(1-Dij)log2(1-Dij) The entropy value of the indirect trust value obtained according to the step 6) is H (R)ij)＝-Rijlog2Rij-(1-Rij)log2(1-Rij) Using entropy values to construct adaptive weights for direct confidence values of
Figure BDA0003172961190000027
Adaptive weights for constructing indirect trust values using entropy values are
Figure BDA0003172961190000028
8) And (3) calculating a complete trust value: calculating the complete trust value of i to j according to the self-adaptive weight of the direct trust value and the indirect trust value obtained in the step 7) and the direct trust value and the indirect trust value obtained in the steps 3) and 6) as follows:
Tij＝wD×Dij+wR×Rij
9) and (3) complete trust value self-adaptive weight calculation: if m evaluation subject terminals evaluate j, m complete trust values can be obtained according to the step 8), and the entropy value of each complete trust value is H (T)ij)＝-Tijlog2Tij-(1-Tij)log2(1-Tij) And constructing the self-adaptive weight of the complete trust value by using the entropy value:
Figure BDA0003172961190000031
10) and (3) calculating a comprehensive trust value: calculating the comprehensive trust value of the network pair j into
Figure BDA0003172961190000032
Advantageous effects
The invention discloses a self-adaptive entropy weight-based electric power Internet of things intelligent terminal trusted computing trust value obtaining method, which has the following characteristics:
the intelligent terminal of the power internet of things is easily attacked in the network such as switching attack, collusion attack, defamation attack and the like in the interactive business of the multi-energy form interconnection and wide users and electric equipment, and brings great potential safety hazards to the network. Aiming at the defect that the traditional trust evaluation system only considers the historical interaction record of a single evaluation subject to cause that the trust value cannot reflect the overall credit condition of an object in a network, the invention provides the method for acquiring the trusted computing trust value of the intelligent terminal of the power internet of things based on the adaptive entropy weight by fully considering the interaction characteristic of the intelligent terminal of the power internet of things in the network and the internal attack characteristic of the network initiated by the untrusted terminal. The method comprises the steps of firstly calculating a direct trust value through a credibility statistical probability model based on beta distribution, then adopting entropy values to construct sub-indirect trust value self-adaptive weights from different recommendation terminals, aiming at the one-sided problem of complete trust value evaluation only consisting of the direct trust value and the indirect trust value, introducing a multi-evaluation-subject comprehensive trust value constructed by the self-adaptive entropy value weights, and improving the identification accuracy. Through experimental data analysis, compared with the existing algorithm, the method has higher accuracy and recall rate under different terminal densities and different malicious node proportions.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the principles of the invention. In the drawings:
FIG. 1 is a diagram of a synthetic trust value establishment path;
FIG. 2 is an algorithm implementation flow;
FIG. 3 shows accuracy and recall at different terminal densities;
fig. 4 shows the precision rate and recall rate for different ratios of malicious terminals.
Detailed Description
The following detailed description of embodiments of the present invention is provided in connection with the accompanying drawings and examples. The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
According to the method for obtaining the credible calculation trust value of the intelligent terminal of the power internet of things based on the adaptive entropy weight, the direct trust value is calculated through a credibility statistical probability model based on beta distribution in the early stage, then the entropy is adopted to construct the adaptive weight of the sub-indirect trust values from different recommendation terminals, and finally the multi-evaluation-subject comprehensive trust value constructed by the adaptive entropy weight is introduced, so that the problem of complete trust value evaluation one-sidedness consisting of the direct trust value and the indirect trust value is solved, and the identification accuracy is improved.
The method comprises the following steps: trust value initialization
Defining a complete trust value obtained by evaluating a terminal j by an intelligent terminal i of the power internet of things as Tij，
Figure BDA0003172961190000041
TijThe closer to 1, the higher the credibility of j is, the trust values of the terminal in the initial state are all set to 0.5, namely the terminal equipment is considered to be credible to a certain extent, so that the problem of ID counterfeiting can be solved, and the initialization time can be shortened.
Step two: trust value parameter extraction
The intelligent terminals in the power Internet of things are interactively cooperated according to application requirements, whether interaction is successful or not is judged by taking the communication channel establishment time t and the communication data quantity q between the terminals as standards, and an interaction result is defined as
Figure BDA0003172961190000042
When the terminal i and the terminal j need to interact, if t is smaller than a certain threshold tthrAnd the communication data quantity q is higher than a certain threshold q after the interaction is finishedthrThen the interaction is defined as successful, otherwise the interaction is defined as failed interaction. Cumulative successful interaction times S between terminal i and terminal jijAnd accumulated number of interaction failures FijIn order to calculate the parameters needed by the trust value, the terminal records the interaction result after each interaction, and the trust parameters are generated and then stored locallyStoring and continuously updating along with interaction;
step three: direct trust value calculation
The direct credit evaluation result of the evaluation subject terminal i on the evaluation object terminal j according to the historical interaction condition is recorded as a direct credit value DijThe beta distribution is taken as a credible statistical probability model, and can be well fitted with credible distribution, and the probability density function is as follows:
Figure BDA0003172961190000043
the mathematical expectation of the beta distribution probability density function is used as a direct trust value of terminal evaluation, and the calculation method comprises the following steps:
Figure BDA0003172961190000044
step four: indirect trust value calculation
1) Child indirect trust value calculation
The indirect trust value is the indirect credit evaluation of j acquired by i from a recommendation terminal x, the recommendation terminal x is a terminal which can interact with both i and j, and the method for acquiring the sub-indirect trusted computing trust value from the recommendation terminal x comprises the following steps:
Figure BDA0003172961190000045
2) sub-indirect trust value adaptive weight calculation
If i evaluates j, n recommendation terminals exist, n sub indirect trust values can be obtained according to the step four 1), and the entropy value of each sub indirect trust value is as follows:
Figure BDA0003172961190000046
the adaptive weight for constructing the sub-indirect trust value by using the entropy value is as follows:
Figure BDA0003172961190000051
3) indirect trust value calculation
Calculating the indirect trust value of i to j according to the self-adaptive weight of the sub indirect trust value obtained in the step 2) and the sub indirect trust value obtained in the step four 1):
Figure BDA0003172961190000052
step five: complete trust value calculation
1) Adaptive weight calculation of direct trust value and indirect trust value
The entropy value of the direct trust value obtained according to the step three is as follows:
H(Dij)＝-Dijlog2Dij-(1-Dij)log2(1-Dij)
the entropy value of the indirect trust value obtained according to the step four is as follows:
H(Rij)＝-Rijlog2Rij-(1-Rij)log2(1-Rij)
the adaptive weights for constructing the direct trust value using the entropy values are:
Figure BDA0003172961190000053
the adaptive weight for constructing the indirect trust value by using the entropy value is as follows:
Figure BDA0003172961190000054
2) complete trust value calculation
Calculating the complete trust value of i to j according to the self-adaptive weight of the direct trust value and the indirect trust value obtained in the step five 1) and the direct trust value and the indirect trust value obtained in the step three and the step four as follows:
Tij＝wD×Dij+wR×Rij
step six: integrated trust value calculation
1) Complete trust value adaptive weight calculation
If m evaluation subject terminals evaluate j, m complete trust values can be obtained according to the fifth step, and the entropy value of each complete trust value is as follows:
H(Tij)＝-Tijlog2Tij-(1-Tij)log2(1-Tij)
the adaptive weights for constructing the complete confidence value using entropy values are:
Figure BDA0003172961190000061
2) integrated trust value calculation
Calculating the comprehensive trust value of the network to j according to the self-adaptive weight of the complete trust value obtained in the step six 1) and the complete trust value obtained in the step five as follows:
Figure BDA0003172961190000062
in order to verify the effectiveness of the method for acquiring the trusted computing trust value of the intelligent terminal of the power internet of things based on the adaptive entropy weight, a typical power wireless private network example is adopted for carrying out the trusted computing verification of the intelligent terminal. Assuming that the communication, storage and calculation capabilities of each intelligent terminal are the same, the intelligent terminals are distributed in a power supply area of 600m × 600m, and the communication radius is 60 m. In order to simulate different terminal densities and ensure network simplicity, the number of neighbors of each terminal is respectively 2, 4 and 8 when the number of intelligent terminals is set to be 25, 100 and 225 in logical connection. By adjusting trust parameters, malicious attack behaviors are simulated, and compared with the traditional single evaluation subject scheme LTMBE, the comprehensive trust value evaluation effect of the scheme is analyzed. The complete simulation parameters are shown in table 1.
Table 1 simulation parameter settings
Figure BDA0003172961190000063
The invention adopts the precision rate gamma and the recall rate eta which are widely used for evaluating the accuracy in the machine learning and the information retrieval as the evaluation indexes of the credible calculation trust value acquisition method, and the two parameters are defined as follows:
Figure BDA0003172961190000064
Figure BDA0003172961190000065
wherein N istrue_negtivesFor the number of detected true malicious terminals, Nfalse_negtivesFor the number of detected false malicious terminals, Nfalse_positivesThe number of undetected true malicious terminals.
By the adoption of the self-adaptive entropy weight-based electric power Internet of things intelligent terminal trusted computing trust value obtaining method, accuracy and recall rate under different terminal densities and malicious terminal proportions are analyzed respectively. And adopting a unified standard to judge the false positive condition of the normal terminal with the comprehensive trust value lower than 0.7 and the false negative condition of the malicious terminal with the trust value higher than 0.35. To eliminate the randomness of the experimental data, 50 runs were performed per experiment, and the statistical results were averaged. Fig. 3 is a simulation result of different terminal densities when the malicious terminal ratio is 20%, and fig. 4 is a simulation result of different malicious terminal ratios when the number of terminals is 100.
As can be seen from fig. 3, the accuracy and recall of the method of the present invention are always higher than those of the comparative LTMBE algorithm, regardless of the low or dense terminal density in the network. Particularly, the method is obviously higher than a comparison method in the rising degree of the accuracy rate, and the accuracy rate can reach about 76% when the number of the terminals is 225, and is improved by nearly 35% compared with an LTMBE algorithm. This is because, in consideration of a plurality of evaluation subjects, as the terminal density increases, each subject can obtain real data from more good terminals, thereby greatly improving the accuracy rate and embodying the validity of the comprehensive trust value.
As can be seen from fig. 4, the accuracy and recall ratio of the method of the present invention are also always higher than those of the comparison method under different malicious node ratios. With the gradual increase of the proportion of the malicious nodes, the number of the false positive normal terminals is lower than that of the true positive malicious terminals, so that the accuracy rate gradually rises. Although the recall rate is gradually reduced, the recall rate can still be maintained at a higher level of about 71% under the condition of 30% of malicious nodes, and the comprehensive trust value has higher evaluation accuracy.

Claims (4)

1. A trusted computing trust value obtaining method for an intelligent terminal of an electric power internet of things based on self-adaptive entropy weight is characterized by comprising the following steps: the method is operated in a distributed mode by electric power internet of things terminal devices based on self-organizing communication connection, and comprises the following stages:
1) and (3) initializing a trust value: defining a complete trust value obtained by evaluating a terminal j by an intelligent terminal i of the power internet of things as Tij，
Figure FDA0003172961180000011
TijThe closer to 1, the higher the credibility of j is, the trust values of the initial state terminal are all set to 0.5, namely the terminal equipment is considered to be credible to a certain extent;
2) and (3) extracting a trust value parameter: the intelligent terminals in the power Internet of things are interactively cooperated according to application requirements, and the accumulated interaction success times S between the terminal i and the terminal jijAnd accumulated number of interaction failures FijIn order to calculate parameters required by the trust value, the terminal records the interaction result after each interaction, generates the trust parameters, and then locally stores the trust parameters and continuously updates the trust parameters along with the interaction;
3) direct trust value calculation: the direct credit evaluation result of the evaluation subject terminal i on the evaluation object terminal j according to the historical interaction condition is recorded as a direct credit value DijThe calculation method comprises the following steps:
Figure FDA0003172961180000012
4) and (3) calculating a sub indirect trust value: the indirect trust value is the indirect trust evaluation of j acquired by i from a recommending terminal x, the recommending terminal x is a terminal which can interact with both i and j, and the sub indirect trust value from the recommending terminal x is calculated:
Figure FDA0003172961180000013
5) and (3) calculating the adaptive weight of the sub indirect trust value: if i evaluates j, n recommendation terminals exist, n sub indirect trust values can be obtained according to the step 4), and the entropy value of each sub indirect trust value is
Figure FDA0003172961180000014
Constructing adaptive weights for the sub-indirect trust values using entropy values:
Figure FDA0003172961180000015
6) and (3) indirect trust value calculation: calculating the indirect trust value of i to j as
Figure FDA0003172961180000016
7) And (3) self-adaptive weight calculation of the direct trust value and the indirect trust value: entropy of the direct trust value obtained according to step 3) is H (D)ij)＝-Dijlog2Dij-(1-Dij)log2(1-Dij) The entropy value of the indirect trust value obtained according to the step 6) is H (R)ij)＝-Rijlog2Rij-(1-Rij)log2(1-Rij) Using entropy values to construct adaptive weights for direct confidence values of
Figure FDA0003172961180000017
Adaptive weights for constructing indirect trust values using entropy values are
Figure FDA0003172961180000021
8) And (3) calculating a complete trust value: calculating the complete trust value of i to j according to the self-adaptive weight of the direct trust value and the indirect trust value obtained in the step 7) and the direct trust value and the indirect trust value obtained in the steps 3) and 6) as follows:
Tij＝wD×Dij+wR×Rij
9) and (3) complete trust value self-adaptive weight calculation: if m evaluation subject terminals evaluate j, m complete trust values can be obtained according to the step 8), and the entropy value of each complete trust value is H (T)ij)＝-Tijlog2Tij-(1-Tij)log2(1-Tij) And constructing the self-adaptive weight of the complete trust value by using the entropy value:
Figure FDA0003172961180000022
10) and (3) calculating a comprehensive trust value: calculating the comprehensive trust value of the network pair j into
Figure FDA0003172961180000023
2. The method for acquiring the trusted computing trust value of the intelligent terminal of the power internet of things based on the adaptive entropy weight as claimed in claim 1, wherein: step 2) judging whether the interaction is successful or not by taking the communication channel establishment time t and the communication data quantity q between the terminals as standards, wherein the interaction result is defined as
Figure FDA0003172961180000024
3. The method for acquiring the trusted computing trust value of the intelligent terminal of the power internet of things based on the adaptive entropy weight as claimed in claim 1, wherein: the step 3) takes the beta distribution as a credibility statistical probability model, can be well fitted with credibility distribution, and has a probability density function as follows:
Figure FDA0003172961180000025
the mathematical expectation of the probability density function is adopted as a direct trust value of the terminal evaluation.
4. The method for acquiring the trusted computing trust value of the intelligent terminal of the power internet of things based on the adaptive entropy weight as claimed in claim 1, wherein: the comprehensive trust value obtained in the step 10) is a final evaluation index of the network on the credibility of the intelligent terminal, reflects the credibility of the terminal in the network, and can identify the terminal which is likely to be invaded in the network or the selfish terminal through the comprehensive trust value.
CN202110823978.8A 2021-07-21 2021-07-21 Electric power Internet of things intelligent terminal trusted computing trust value obtaining method based on self-adaptive entropy value weight Pending CN113672932A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110823978.8A CN113672932A (en) 2021-07-21 2021-07-21 Electric power Internet of things intelligent terminal trusted computing trust value obtaining method based on self-adaptive entropy value weight

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110823978.8A CN113672932A (en) 2021-07-21 2021-07-21 Electric power Internet of things intelligent terminal trusted computing trust value obtaining method based on self-adaptive entropy value weight

Publications (1)

Publication Number Publication Date
CN113672932A true CN113672932A (en) 2021-11-19

Family

ID=78539745

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110823978.8A Pending CN113672932A (en) 2021-07-21 2021-07-21 Electric power Internet of things intelligent terminal trusted computing trust value obtaining method based on self-adaptive entropy value weight

Country Status (1)

Country Link
CN (1) CN113672932A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114553458A (en) * 2021-12-16 2022-05-27 国网河北省电力有限公司信息通信分公司 Method for establishing and dynamically maintaining credible group in power Internet of things environment

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103297956A (en) * 2013-05-06 2013-09-11 北京航空航天大学 Dynamic lightweight class trust evaluation method based on Bayesian theory and entropy theory
CN107750053A (en) * 2017-05-25 2018-03-02 天津大学 Based on multifactor wireless sensor network dynamic trust evaluation system and method

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103297956A (en) * 2013-05-06 2013-09-11 北京航空航天大学 Dynamic lightweight class trust evaluation method based on Bayesian theory and entropy theory
CN107750053A (en) * 2017-05-25 2018-03-02 天津大学 Based on multifactor wireless sensor network dynamic trust evaluation system and method

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114553458A (en) * 2021-12-16 2022-05-27 国网河北省电力有限公司信息通信分公司 Method for establishing and dynamically maintaining credible group in power Internet of things environment

Similar Documents

Publication Publication Date Title
Lian et al. An intrusion detection method based on decision tree-recursive feature elimination in ensemble learning
Sala et al. Measurement-calibrated graph models for social network experiments
CN108718310A (en) Multi-level attack signatures generation based on deep learning and malicious act recognition methods
Xue et al. An evolutionary computation based feature selection method for intrusion detection
Yuan et al. Higher-order structure based anomaly detection on attributed networks
CN110263538A (en) A kind of malicious code detecting method based on system action sequence
CN114372530A (en) Abnormal flow detection method and system based on deep self-coding convolutional network
Aissa et al. A genetic clustering technique for Anomaly-based Intrusion Detection Systems
CN114511131A (en) Network security situation prediction method and system based on machine learning algorithm
CN116633615A (en) Access control method based on blockchain and risk assessment
CN113672932A (en) Electric power Internet of things intelligent terminal trusted computing trust value obtaining method based on self-adaptive entropy value weight
Höner et al. Minimizing trust leaks for robust sybil detection
CN114003960A (en) Training method of neural network model
Li et al. FlowGANAnomaly: Flow-Based Anomaly Network Intrusion Detection with Adversarial Learning
Devi et al. Stochastic Gradient Boosting Model for Twitter Spam Detection.
CN116346638B (en) Data tampering inference method based on power grid power and alarm information interaction verification
CN110889467A (en) Company name matching method and device, terminal equipment and storage medium
Chen et al. Dynamic threshold strategy optimization for security protection in Internet of Things: An adversarial deep learning‐based game‐theoretical approach
CN115242556A (en) Network anomaly detection method based on incremental self-encoder
Bharathi et al. Enhanced security for an IoT devices in cyber-physical system against cyber attacks
CN115333806A (en) Penetration test attack path planning method and device, electronic equipment and storage medium
Xie et al. Research and application of intrusion detection method based on hierarchical features
Yin et al. A network security situation assessment model based on BP neural network optimized by DS evidence theory
Zhang et al. Multi-round data poisoning attack and defense against truth discovery in crowdsensing systems
Masoumzadeh et al. Preserving structural properties in anonymization of social networks

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