CN112769654A - Modbus TCP protocol fuzzy test method based on genetic algorithm - Google Patents

Modbus TCP protocol fuzzy test method based on genetic algorithm Download PDF

Info

Publication number
CN112769654A
CN112769654A CN202110082910.9A CN202110082910A CN112769654A CN 112769654 A CN112769654 A CN 112769654A CN 202110082910 A CN202110082910 A CN 202110082910A CN 112769654 A CN112769654 A CN 112769654A
Authority
CN
China
Prior art keywords
individual
individuals
test case
fitness
population
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
CN202110082910.9A
Other languages
Chinese (zh)
Inventor
杨文�
郭志民
车欣
周劼英
王丹
吕卓
李斌
张铮
李暖暖
蔡军飞
李鸣岩
陈岑
张伟
谢辰承
时子昱
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.)
Hangzhou Uwntek Automation System Co ltd
State Grid Corp of China SGCC
Electric Power Research Institute of State Grid Henan Electric Power Co Ltd
Original Assignee
Hangzhou Uwntek Automation System Co ltd
State Grid Corp of China SGCC
Electric Power Research Institute of State Grid Henan 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 Hangzhou Uwntek Automation System Co ltd, State Grid Corp of China SGCC, Electric Power Research Institute of State Grid Henan Electric Power Co Ltd filed Critical Hangzhou Uwntek Automation System Co ltd
Priority to CN202110082910.9A priority Critical patent/CN112769654A/en
Publication of CN112769654A publication Critical patent/CN112769654A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/18—Protocol analysers

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

The invention discloses a fuzzy test method for a Modbus TCP (transmission control protocol) based on a genetic algorithm. Firstly, establishing a fuzzy test case queue for storing the sent fuzzy test cases and abnormal codes in a response message of the tested PLC after receiving the test cases; secondly, according to the length of a code path covered by the abnormal code, different weight values are given to different abnormal codes; and finally, when the individual fitness is calculated by a genetic algorithm, calculating from the similarity between the individual and the seeds in the seed queue and the abnormal codes of the seeds, thereby realizing the aim of adjusting the generation of the fuzzy test case according to the feedback of the tested PLC. The method has the characteristics of low redundancy rate, high response rate and the like of the constructed test case, and can greatly improve the fuzzy test efficiency of the Modbus TCP protocol.

Description

Modbus TCP protocol fuzzy test method based on genetic algorithm
Technical Field
The invention belongs to a Modbus TCP protocol fuzzy test technology, and particularly relates to a Modbus TCP protocol fuzzy test method based on a genetic algorithm.
Background
With the continuous development of industrial internet and the continuous integration of informatization and industrialization, the traditional industrial control system is more and more closely connected with the internet. Originally, only the industrial control system designed for communication in the intranet gradually accesses the internet, which increases the openness and interconnectivity of the industrial control system and improves the productivity, and simultaneously causes the traditional industrial control system to face more and more security threats from the internet. Fuzz testing is a method of mining potential vulnerabilities of software primarily through unexpected inputs and monitoring of anomalous results. The protocol fuzzy test is to construct a malformed data packet, send the malformed data packet to the tested industrial control equipment and monitor whether the industrial control equipment is abnormal, so as to mine the security holes of the industrial control equipment.
The existing protocol fuzz test research has the following defects: a) a known protocol format is required, and the effective fuzzing test cannot be carried out on the proprietary protocol with the unknown format; b) the response rate of the test case is low, when fuzzy test tools such as Peach and the like carry out fuzzy test on an industrial control protocol, a large number of specially constructed malformed data packets can be generated, the formats of a large number of data packets can not be identified by the tested equipment, and the tested equipment can not directly respond to the request data packets; c) due to the diversity of the test cases, when the test cases are constructed, a targeted test set aiming at different types of vulnerability structures is not considered, so that the test success rate is low; d) due to the redundancy of the test cases, Peach may generate a large amount of redundant malformed data packets, which results in low efficiency of the fuzzy test.
Disclosure of Invention
Therefore, the technical problem to be solved by the invention is that the fuzzy test method for the Modbus TCP protocol in the prior art can perform automatic fuzzy test on all industrial control equipment supporting a specific protocol, but has the problems of low response rate, high redundancy and the like of a fuzzy test case. When the method of the invention is used for generating the Modbus TCP protocol fuzzy test case by using the genetic algorithm, the fitness value of the individual is evaluated from the two aspects of the similarity between the individual and the seeds in the seed queue and the abnormal codes of the seeds, so that the generation process of the fuzzy test case is adjusted according to the feedback of the tested PLC, and the test case which is more likely to trigger collapse is screened out.
In order to achieve the purpose, the technical scheme of the invention is as follows: a Modbus TCP protocol fuzzy test method based on a genetic algorithm comprises the following steps:
s1: according to the length of the code coverage path, different weight values are given to different abnormal codes of the Modbus TCP;
s2: encoding individuals, namely test cases, by using a Gray encoding mode to form a genetic algorithm initial generation population;
s3: calculating the fitness of the individual;
s4: screening out parent individuals crossed in the next step by using a roulette selection operator according to the calculated individual fitness;
s5: randomly generating a cross point for two individuals selected in S4 according to the cross probability PcTo swap chromosomes after the crossover sites of two individuals, generating offspring individuals:
s6: according to the mutation probability PmCarrying out mutation on the gene sequence of the individual according to a basic position mutation operator;
s7: judging whether the maximum iteration algebra is reached, and if so, jumping to S8; otherwise jump to S3;
s8: calculating the fitness values of all individuals in the current population, decoding the individual with the maximum fitness value, namely the optimal individual to obtain a generated fuzzy test case, inputting the test case into a format analysis module of a Peach Fuzzer, and finally inputting the test case into a programmable logic controller through an interactive release module;
s9: judging whether the industrial control equipment is down or not through an agent monitoring module of the Peach Fuzzer; if the system is down, stopping; if the system crash does not occur, executing S9;
s10: the response data packet of the tested programmable logic controller is obtained through the agent monitoring module of the Peach Fuzzer, the format analysis module is used for obtaining the abnormal code, the weight of the test case is obtained according to the feedback of the tested PLC, namely the abnormal code in the response message, the output test case and the weight are written into the test case queue, and the step is switched to S3, so that the generation process of the test case is adjusted in real time according to the feedback of the PLC.
Further, in the step S1: the exception code has the longest code coverage path of 4 times, so the weight is the maximum, which is denoted as w4Next are exception code 2, exception code 3 and exception code 1, respectivelyGiven a weight w2、w3And w1If the generated test case is responded normally by the industrial control equipment, namely the constructed test case belongs to a normal data packet, the weight given to the test case is minimum and is marked as w0(ii) a The assignment of exception codes is: w is a0＜w1＜w3＜w2＜w4。
Further, in the step S3, the calculating the fitness of the individual specifically includes the following sub-steps:
s301: creating a test case queue for storing the optimal test case calculated by each genetic algorithm and the weight of the abnormal code in the response message of the tested PLC after receiving the test case; the initial queue consists of Modbus TCP protocol data packets captured when the upper computer and the PLC are in normal communication;
s302: in generating p individualsxThen, all the test cases in the test case queue are compared with the individual pxThe individuals with the same function code form a set Py(ii) a Calculating pxAnd set PyMiddle individual pjThe distance of each byte is accumulated, and p is calculatedxAnd pjThen adding 1 to the calculated individual distance; then take the reciprocal and multiply by pjWeight w calculated from the abnormal code ofjThe formula is as follows:
Figure BDA0002909994370000031
B(px)＝(b0 x,b1 x,…,bx l-1)
B(pj)＝(b0 y,b1 y,…,by l-1)
wherein S (p)x,pj) Representing an individual pxAnd individual pjThe similarity of (2); b (p)x) Representing constituent individuals pxA set of all bytes; l represents an individual pxThe total number of bytes of;
Figure BDA0002909994370000032
representing an individual pxThe value of the j-1 th byte of (1);
s303: p is to bexAnd set PyThe similarity of each individual in (a) is added and divided by the set PyN, to obtain pxAverage similarity to initial population
Figure BDA0002909994370000033
Average similarity
Figure BDA0002909994370000034
As fitness value fitness (p) of the individualx)。
Further, the step S4 has the sub-steps of:
s401: calculating the probability Pro (p) that each individual in the population is inherited from the fitness values of the individuals calculated in step S3i) The calculation formula is as follows:
Figure BDA0002909994370000035
wherein N represents the total number of individuals in the population;
s402: calculating individual p in populationiCumulative probability of (Q)iThe calculation formula is as follows:
Figure BDA0002909994370000041
s403: in [0,1 ]]Generating a random value rand within the interval, if rand<Q1Then choose Individual 1, otherwise choose to satisfy Qk-1≤rand＜QkAnd (4) the selected individuals enter a filial generation population to carry out the next operation.
Further, in the step S5, the cross probability PcThe calculation formula of (a) is as follows:
Figure BDA0002909994370000042
wherein f ismaxRepresenting the maximum value of fitness values of all individuals in the population; f. ofavgRepresenting the average value of fitness values of all individuals in the population; f represents the greater of the fitness values of the two individuals to be crossed; k is a radical of1And k2Is a preset value.
Further, in the step S6, the mutation probability PmThe calculation formula of (a) is as follows:
Figure BDA0002909994370000043
wherein f ismaxRepresenting the maximum value of fitness values of all individuals in the population; f. ofavgRepresenting the average value of fitness values of all individuals in the population; f' represents the fitness value of the individual to be mutated; k is a radical of3And k4Is a preset value.
The invention has the beneficial effects that: when the fuzzy test case of the Modbus TCP protocol is generated by using a genetic algorithm, different weights are given to different abnormal codes in order to achieve the aim of timely modifying the generated test case according to a response message of the PLC, and the fitness value of an individual is evaluated from the aspects of similarity between the individual and the seeds in the seed queue and the abnormal codes of the seeds, so that the generation process of the fuzzy test case is adjusted according to the feedback of the tested PLC, and the test case which is more likely to trigger breakdown is screened out. The test case constructed by the method has the characteristics of low redundancy, high response rate and the like, and the fuzzy test efficiency of the Modbus TCP protocol is greatly improved.
Drawings
FIG. 1 is an architecture diagram of a Modbus TCP protocol fuzzy test method based on a genetic algorithm according to the invention;
FIG. 2 is a flow chart of the Modbus TCP protocol fuzzy test method based on the genetic algorithm.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects solved by the present invention more clearly apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The architecture diagram of the Modbus TCP protocol fuzzy test method based on the genetic algorithm is shown in figure 1, the method is realized based on a fuzzy test system, and the fuzzy test system mainly comprises a fuzzy test case generation module, a Peach Fuzzer and a programmable logic controller module. After the test case is generated by the fuzzy test case generation module, the test case is transmitted to a format analysis module of a Peach Fuzzer, the interactive release module is controlled by the state control module to input the generated fuzzy test case into the tested PLC, meanwhile, the agent monitoring module detects whether the tested PLC collapses or not, if the tested PLC collapses, the log recording module records the test result, and the test is stopped, if the tested PLC does not collapse, the interactive release module acquires a PLC response message, the state control module calls the format analysis module to analyze the response message, and finally, the analysis result is fed back to the fuzzy test case generation module to guide the generation of the next fuzzy test case.
As shown in fig. 2, the method for fuzzing a Modbus TCP protocol based on a genetic algorithm provided by the present invention includes the following steps:
s1: a series of exception codes are set in the Modbus TCP protocol to define the exception events generated. Different exception codes can reflect the length of a code coverage path of the test case, and the longer the code coverage path of the test case is, the more likely the PLC exception is triggered. Therefore, according to the length of the code coverage path, different weight values are given to different abnormal codes in the fuzzy test case generation module;
in this embodiment, the abnormal code has the longest code coverage path of 4 times, so the weight is the largest and is marked as w4Next, the exception code 2, exception code 3 and exception code 1 are given weights w2、w3And w1If the generated test case is normally responded by the industrial control equipment, the test case is constructedIf the test case of (1) belongs to the normal data packet, the weight assigned to the test case is the minimum and is marked as w0The assignment of exception codes is as follows:
w0＜w1＜w3＜w2＜w4
s2: encoding individuals, namely test cases, by using a Gray encoding mode to form a genetic algorithm initial generation population;
s3: calculating the fitness of the individual, wherein the step comprises the following sub-steps:
s301: and creating a test case queue for storing the optimal test case calculated by each genetic algorithm and the weight of the abnormal code in the response message of the tested PLC after receiving the test case. The initial queue consists of Modbus TCP protocol data packets captured when the upper computer and the PLC are in normal communication;
s302: in generating p individualsxThen, all the test cases in the test case queue are compared with the individual pxThe individuals with the same function code form a set Py(ii) a Calculating pxAnd set PyMiddle individual pjThe distance of each byte is accumulated, and p is calculatedxAnd pjThen adding 1 to the calculated individual distance; then take the reciprocal and multiply by pjWeight w calculated from the abnormal code ofjThe formula is as follows:
Figure BDA0002909994370000061
B(px)＝(b0 x,b1 x,…,bx l-1)
B(pj)＝(b0 y,b1 y,…,by l-1)
wherein S (p)x,pj) Representing an individual pxAnd individual pjThe similarity of (2); b (p)x) Representing constituent individuals pxA set of all bytes; l represents an individual pxByte sum ofCounting;
Figure BDA0002909994370000062
representing an individual pxThe value of the j-1 th byte of (1);
s303: p is to bexAnd set PyThe similarity of each individual in (a) is added and divided by the set PyN, to obtain pxAverage similarity to initial population
Figure BDA0002909994370000063
The calculation formula is as follows:
Figure BDA0002909994370000064
s304: average similarity to be finally calculated
Figure BDA0002909994370000065
As fitness value fitness (p) of the individualx) The calculation formula is as follows:
Figure BDA0002909994370000066
s4: and (3) screening out the parent individuals which are crossed in the next step by using a roulette wheel selection operator according to the calculated individual fitness, wherein the step comprises the following substeps:
s401: the fitness value of the individual is calculated in step S304, and the probability Pro (p) that each individual in the population is inherited is calculatedi) The calculation formula is as follows:
Figure BDA0002909994370000071
wherein N represents the total number of individuals in the population;
s402: calculating individual p in populationiCumulative probability of (Q)iThe calculation formula is as follows:
Figure BDA0002909994370000072
s403: then in [0,1 ]]A random value rand is generated within the interval. If rand<Q1Selecting an individual 1, otherwise, selecting an individual k meeting the following formula, and entering the selected individual into a filial generation population for the next operation:
Qk-1≤rand＜Qk
s5: randomly generating a cross point for the two individuals selected in step S4, and calculating the cross probability P according to the following formulacTo swap chromosomes after the crossover sites of two individuals, generating offspring individuals:
Figure BDA0002909994370000073
wherein f ismaxRepresenting the maximum value of fitness values of all individuals in the population; f. ofavgRepresenting the average value of fitness values of all individuals in the population; f represents the greater of the fitness values of the two individuals to be crossed; k is a radical of1And k2Is a preset value.
S6: the mutation probability P is calculated according to the following formulamAnd (4) carrying out mutation on the gene sequences of the individuals according to the basic position mutation operator.
Figure BDA0002909994370000074
Wherein f' represents the fitness value of the individual to be mutated; k is a radical of3And k4Is a preset value.
In the present embodiment, k1～k4The values of (A) are as follows: k is a radical of1＝0.3,k2＝0.9,k3＝0.2,k40.01. According to the test results of different PLCs, k can be matched1～k4The value of (a) is adjusted.
S7: judging whether the maximum iteration algebra is reached, and if so, jumping to S8; otherwise, the process jumps to S3.
S8: and when the maximum iterative algebra is reached, calculating the fitness values of all individuals in the current population, decoding the individual with the maximum fitness value, namely the optimal individual to obtain a generated fuzzy test case, inputting the test case into a format analysis module of a Peach Fuzzer, and finally inputting the test case into the programmable logic controller through an interactive publishing module.
S9: judging whether the industrial control equipment is down or not through an agent monitoring module of the Peach Fuzzer; if the system is down, stopping; if the system downtime does not occur, executing step S9;
s10: and acquiring a response data packet of the tested programmable logic controller through an agent monitoring module of the Peach Fuzzer, acquiring an abnormal code by using a format analysis module, and inputting the abnormal code into a fuzzy test case generation module. And obtaining the weight of the test case in a fuzzy test case generation module according to the feedback of the PLC to be tested, namely the abnormal code in the response message, writing the output test case and the weight into a test case queue, and jumping to S3, thereby realizing the real-time adjustment of the generation process of the test case according to the feedback of the PLC.
It should be understood that the above examples are only for clarity of illustration and are not intended to limit the embodiments. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. And obvious variations or modifications therefrom are within the scope of the invention.

Claims (6)

1. A Modbus TCP protocol fuzzy test method based on a genetic algorithm is characterized by comprising the following steps:
s1: according to the length of the code coverage path, different weight values are given to different abnormal codes of the Modbus TCP;
s2: encoding individuals, namely test cases, by using a Gray encoding mode to form a genetic algorithm initial generation population;
s3: calculating the fitness of the individual;
s4: screening out parent individuals crossed in the next step by using a roulette selection operator according to the calculated individual fitness;
s5: randomly generating a cross point for two individuals selected in S4 according to the cross probability PcTo swap chromosomes after the crossover sites of two individuals, generating offspring individuals:
s6: according to the mutation probability PmCarrying out mutation on the gene sequence of the individual according to a basic position mutation operator;
s7: judging whether the maximum iteration algebra is reached, and if so, jumping to S8; otherwise jump to S3;
s8: calculating the fitness values of all individuals in the current population, decoding the individual with the maximum fitness value, namely the optimal individual to obtain a generated fuzzy test case, inputting the test case into a format analysis module of a Peach Fuzzer, and finally inputting the test case into a programmable logic controller through an interactive release module;
s9: judging whether the industrial control equipment is down or not through an agent monitoring module of the Peach Fuzzer; if the system is down, stopping; if the system crash does not occur, executing S9;
s10: the response data packet of the tested programmable logic controller is obtained through the agent monitoring module of the Peach Fuzzer, the format analysis module is used for obtaining the abnormal code, the weight of the test case is obtained according to the feedback of the tested PLC, namely the abnormal code in the response message, the output test case and the weight are written into the test case queue, and the step is switched to S3, so that the generation process of the test case is adjusted in real time according to the feedback of the PLC.
2. The Modbus TCP protocol fuzzy test method based on the genetic algorithm according to claim 1, wherein in the step S1: the exception code has the longest code coverage path of 4 times, so the weight is the maximum, which is denoted as w4Next, the exception code 2, exception code 3 and exception code 1 are given weights w2、w3And w1If the generated test is usedThe case is normally responded by the industrial control equipment, namely the constructed test case belongs to a normal data packet, the weight given to the test case is minimum and is marked as w0(ii) a The assignment of exception codes is: w is a0＜w1＜w3＜w2＜w4。
3. The Modbus TCP protocol fuzzy test method based on the genetic algorithm according to claim 1 or 2, wherein the step S3 of calculating the fitness of the individual specifically comprises the following substeps:
s301: creating a test case queue for storing the optimal test case calculated by each genetic algorithm and the weight of the abnormal code in the response message of the tested PLC after receiving the test case; the initial queue consists of Modbus TCP protocol data packets captured when the upper computer and the PLC are in normal communication;
s302: in generating p individualsxThen, all the test cases in the test case queue are compared with the individual pxThe individuals with the same function code form a set Py(ii) a Calculating pxAnd set PyMiddle individual pjThe distance of each byte is accumulated, and p is calculatedxAnd pjThen adding 1 to the calculated individual distance; then take the reciprocal and multiply by pjWeight w calculated from the abnormal code ofjThe formula is as follows:
Figure FDA0002909994360000021
B(px)＝(b0 x,b1 x,…,bx l-1)
B(pj)＝(b0 y,b1 y,…,by l-1)
wherein S (p)x,pj) Representing an individual pxAnd individual pjThe similarity of (2); b (p)x) Representing constituent individuals pxA set of all bytes; l meterSample pxThe total number of bytes of; bj xRepresenting an individual pxThe value of the j-1 th byte of (1);
s303: p is to bexAnd set PyThe similarity of each individual in (a) is added and divided by the set PyN, to obtain pxAverage similarity to initial population
Figure FDA0002909994360000022
Average similarity
Figure FDA0002909994360000023
As fitness value fitness (p) of the individualx)。
4. The Modbus TCP protocol fuzzy test method based on the genetic algorithm of claim 3, wherein the step S4 has the sub-steps of:
s401: calculating the probability Pro (p) that each individual in the population is inherited from the fitness values of the individuals calculated in step S3i) The calculation formula is as follows:
Figure FDA0002909994360000024
wherein N represents the total number of individuals in the population;
s402: calculating individual p in populationiCumulative probability of (Q)iThe calculation formula is as follows:
Figure FDA0002909994360000031
s403: in [0,1 ]]Generating a random value rand within the interval, if rand<Q1Then choose Individual 1, otherwise choose to satisfy Qk-1≤rand＜QkAnd (4) the selected individuals enter a filial generation population to carry out the next operation.
5. The Modbus TCP protocol fuzzy test method based on genetic algorithm according to claim 1, wherein in the step S5, the cross probability P iscThe calculation formula of (a) is as follows:
Figure FDA0002909994360000032
wherein f ismaxRepresenting the maximum value of fitness values of all individuals in the population; f. ofavgRepresenting the average value of fitness values of all individuals in the population; f represents the greater of the fitness values of the two individuals to be crossed; k is a radical of1And k2Is a preset value.
6. The Modbus TCP protocol fuzzy test method based on genetic algorithm according to claim 1, wherein in the step S6, the mutation probability P ismThe calculation formula of (a) is as follows:
Figure FDA0002909994360000033
wherein f ismaxRepresenting the maximum value of fitness values of all individuals in the population; f. ofavgRepresenting the average value of fitness values of all individuals in the population; f' represents the fitness value of the individual to be mutated; k is a radical of3And k4Is a preset value.
CN202110082910.9A 2021-01-21 2021-01-21 Modbus TCP protocol fuzzy test method based on genetic algorithm Pending CN112769654A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110082910.9A CN112769654A (en) 2021-01-21 2021-01-21 Modbus TCP protocol fuzzy test method based on genetic algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110082910.9A CN112769654A (en) 2021-01-21 2021-01-21 Modbus TCP protocol fuzzy test method based on genetic algorithm

Publications (1)

Publication Number Publication Date
CN112769654A true CN112769654A (en) 2021-05-07

Family

ID=75702386

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110082910.9A Pending CN112769654A (en) 2021-01-21 2021-01-21 Modbus TCP protocol fuzzy test method based on genetic algorithm

Country Status (1)

Country Link
CN (1) CN112769654A (en)

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113765718A (en) * 2021-09-10 2021-12-07 烽火通信科技股份有限公司 Test topology construction method and device for QUIC protocol
CN114465938A (en) * 2022-01-05 2022-05-10 国网湖北省电力有限公司电力科学研究院 Penetration testing method, system and storage medium of charging pile CAN protocol based on fuzzy testing
CN115203061A (en) * 2022-09-14 2022-10-18 广东美的暖通设备有限公司 Interface automation test method and device, electronic equipment and storage medium
CN115225551A (en) * 2022-07-14 2022-10-21 北京邮电大学 Fuzzy test method, device, equipment and storage medium
CN116094972A (en) * 2023-01-18 2023-05-09 重庆邮电大学 Modbus TCP protocol fuzzy test method based on QRNN neural network
CN116204445A (en) * 2023-04-27 2023-06-02 苏州浪潮智能科技有限公司 Test case generation method and device, code test method, device and medium
CN116633830A (en) * 2023-05-25 2023-08-22 哈尔滨工业大学 Seed mutation operation scheduling method based on firefly algorithm
CN116841243A (en) * 2023-06-19 2023-10-03 浙江大学 Intelligent PLC protocol format deducing method, fuzzy test method and device
CN117591396A (en) * 2023-10-25 2024-02-23 国网湖北省电力有限公司宜昌供电公司 Modbus TCP protocol test case generation method and system

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105721255A (en) * 2016-04-14 2016-06-29 北京工业大学 Industrial control protocol vulnerability mining system based on fuzzy test
US20180365139A1 (en) * 2017-06-15 2018-12-20 Microsoft Technology Licensing, Llc Machine learning for constrained mutation-based fuzz testing
CN110113227A (en) * 2019-04-18 2019-08-09 上海大学 A kind of fuzz testing method for generating test case that variation encodes certainly

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105721255A (en) * 2016-04-14 2016-06-29 北京工业大学 Industrial control protocol vulnerability mining system based on fuzzy test
US20180365139A1 (en) * 2017-06-15 2018-12-20 Microsoft Technology Licensing, Llc Machine learning for constrained mutation-based fuzz testing
CN110113227A (en) * 2019-04-18 2019-08-09 上海大学 A kind of fuzz testing method for generating test case that variation encodes certainly

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
项力等: "基于遗传算法的Modbus TCP协议模糊测试技术研究", 《舰船电子工程》 *

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113765718A (en) * 2021-09-10 2021-12-07 烽火通信科技股份有限公司 Test topology construction method and device for QUIC protocol
CN113765718B (en) * 2021-09-10 2023-06-09 烽火通信科技股份有限公司 QUIC protocol-oriented test topology construction method and device
CN114465938A (en) * 2022-01-05 2022-05-10 国网湖北省电力有限公司电力科学研究院 Penetration testing method, system and storage medium of charging pile CAN protocol based on fuzzy testing
CN115225551A (en) * 2022-07-14 2022-10-21 北京邮电大学 Fuzzy test method, device, equipment and storage medium
CN115225551B (en) * 2022-07-14 2024-03-29 北京邮电大学 Fuzzy test method, device, equipment and storage medium
CN115203061A (en) * 2022-09-14 2022-10-18 广东美的暖通设备有限公司 Interface automation test method and device, electronic equipment and storage medium
CN116094972A (en) * 2023-01-18 2023-05-09 重庆邮电大学 Modbus TCP protocol fuzzy test method based on QRNN neural network
CN116094972B (en) * 2023-01-18 2024-05-07 重庆邮电大学 Modbus TCP protocol fuzzy test method based on QRNN neural network
CN116204445A (en) * 2023-04-27 2023-06-02 苏州浪潮智能科技有限公司 Test case generation method and device, code test method, device and medium
CN116633830A (en) * 2023-05-25 2023-08-22 哈尔滨工业大学 Seed mutation operation scheduling method based on firefly algorithm
CN116633830B (en) * 2023-05-25 2024-01-23 哈尔滨工业大学 Seed mutation operation scheduling method based on firefly algorithm
CN116841243A (en) * 2023-06-19 2023-10-03 浙江大学 Intelligent PLC protocol format deducing method, fuzzy test method and device
CN116841243B (en) * 2023-06-19 2024-01-09 浙江大学 Intelligent PLC protocol format deducing method, fuzzy test method and device
CN117591396A (en) * 2023-10-25 2024-02-23 国网湖北省电力有限公司宜昌供电公司 Modbus TCP protocol test case generation method and system

Similar Documents

Publication Publication Date Title
CN112769654A (en) Modbus TCP protocol fuzzy test method based on genetic algorithm
CN116094972B (en) Modbus TCP protocol fuzzy test method based on QRNN neural network
CN112104525A (en) DNP3 protocol fuzzy test method based on sequence generation countermeasure network
CN114064471A (en) Ethernet/IP protocol fuzzy test method based on generation of countermeasure network
CN117596119A (en) Equipment data acquisition and monitoring method and system based on SNMP (simple network management protocol)
Njoya et al. Evolutionary-based wireless sensor deployment for target coverage
CN114070655B (en) Network flow detection rule generation method and device, electronic equipment and storage medium
Sun et al. Maskfuzzer: A maskgan-based industrial control protocol fuzz testing framework
Nguyen et al. Towards improving explainability, resilience and performance of cybersecurity analysis of 5G/IoT networks (work-in-progress paper)
CN117061236A (en) Fuzzy test method for network protocol
Liu et al. Predicting malfunction of mobile network base station using machine learning approach
Gnanaprasanambikai et al. Survey of genetic algorithm effectiveness in intrusion detection
Ezzarii et al. Epigenetic algorithm for performing intrusion detection system
CN114063606B (en) PLC protocol fuzzy test method and device, electronic equipment and storage medium
CN115333915A (en) Network management and control system for heterogeneous host
Rai et al. Genetic algorithm based intrusion detection system
Garzia et al. New technique for the optimization of security communication wired networks in historical buildings
CN117610027B (en) Private protocol vulnerability detection method and system
CN118659972B (en) Deep learning-based concentrator optimal configuration method and system
Sweeten et al. Cyber-Physical GNN-Based Intrusion Detection in Smart Power Grids
CN118473826B (en) Multi-network port protection method and device, electronic equipment and storage medium
CN114363095B (en) System vulnerability analysis method, system and medium based on petri net
Lee et al. Node aging effect on connectivity of data gathering trees in sensor networks
Qin et al. Research and Implementation of Fuzzy Test Method Based on Multi-armed Bandit
CN113852608B (en) Firewall rule exception handling optimization method based on gene formula

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20210507

RJ01 Rejection of invention patent application after publication