Fuzzy test case generation system and method based on coupling auto-encoder

Abstract

The invention discloses a fuzzy test case generation system based on a coupling auto-encoder. The fuzzy test case generation system comprises a sample set construction module, a coupling auto-encoder module and a fuzzy test module; the sample set construction module is used for generating a data training set; the coupling auto-encoder module is used for generating a test case; and the fuzzy test module is used for detecting and analyzing the test case. The invention also discloses a fuzzy test case generation method based on the coupling auto-encoder. The method comprises the following steps: S1, generating a data training set; S2, generating a test case; and S3, detecting, judging and analyzing the test case, and continuously optimizing the data training set. According to the invention, the data training set can be continuously optimized, the adaptability of the test case is improved, the generated test case not only meets grammar requirements of a data protocol format, but also has the characteristics of abnormal or vulnerability data, the acceptance rate of the test case and the trigger rate of vulnerabilities are improved, the method can be applied to various different industrial control network protocols, and wide application prospects are realized.

Description

technical field [0001] The invention relates to the field of industrial network security, in particular to a system and method for generating fuzzy test cases based on coupled autoencoders. Background technique [0002] With the rapid development of network technology, the industrial control system has developed from the original centralized control system to field bus and network control system. At present, the network control system has been widely used in various fields of the national economy, and it is more and more closely related to people's production and life. Since the protocol format of most industrial control network protocols is designed as short frame and unencrypted, and the protocol details such as boundary value and field relationship have not been perfected, normal communication is easy to be intercepted and used. Once discovered and used by hackers, Not only will it cause serious safety hazards to the control system, but it will even lead to major losses ...

AI Technical Summary

Problems solved by technology

At present, many fuzz testing technologies generate test cases by manually parsing protocol messages, using the framework to provide field definition protocols, so that the generated messages can conform to the required protocol format, and then send the messages to the device for testing , so as to enter a deeper test path, but the disadvantage of this type of fuzz testing technology is that the writing of each test path requires a lot of manpower, and the test efficiency is not high

Images