Source node loophole detection method based on integrated neural network

Abstract

The invention provides a source node loophole detection method based on an integrated neural network. Source nodes are processed with an N-Gram algorithm, and a represented by an N-Gram set; implicit characteristics are mined from the N-Gram set with a probability statistics method, so that the attribute of code content is ensured, and the sequence correlation property among the codes is kept; characteristic selection is performed with a ReliefF algorithm to calculate a characteristic weight; specific to the aim of solving extreme imbalance of sample data, the functions of small type samples need to be fully considered during calculation, and different neighbor values are set for different types so that the characteristics of the small sample data can play certain roles in calculation; a multilayer feed-forward network is trained with a BP algorithm in the neural network for serving as individual networks, the trust scope of each individual network is learned through a series of parameter learning of identification rate, reject rate and the like with a DS evidence theory, and a final detection result is summarized according to different trust values of each network, so that accurate and effective source node loophole detection is realized.

Description

technical field [0001] The invention relates to a detection method, in particular to a source code vulnerability detection method based on an integrated neural network. Background technique [0002] With the increasing number of hacker attacks and the proliferation of worms on the Internet, information security has gradually become the focus of people's eyes. A core problem in information security is the software security loopholes in computer systems. Malicious attackers can use these security loopholes to elevate their privileges, access unauthorized resources, and even destroy sensitive data. [0003] The heavy losses caused by software security loopholes and the increasing number of loopholes have made people realize the importance of software security. Since the 1990s, information security scholars and computer security researchers have begun to study computer security vulnerabilities, the most well-known of which is the buffer overflow attack vulnerability. However, ...

AI Technical Summary

Problems solved by technology

The detection of software security vulnerabilities requires more complex requirements than earlier standard program analysis techniques used in compiler optimization and software testing bug-finding

Images