A Malware Adversarial Sample Generation Method Combined with API Fuzzing Technology

Abstract

The invention relates to a malicious software countermeasure sample generation method combined with API fuzzy processing technology, and belongs to the technical field of computer and information science. The invention firstly inserts irrelevant API vectors into the original API calling sequence, and initially realizes the confusion of the feature functions of the malware; then implements the obfuscation operation of function call redirection on the samples to hide the function functions of the API; finally, the modified samples are Feed to a malware classifier, check if it achieves misclassification, solve an optimization problem using a genetic algorithm. The present invention has higher practicability and is more in line with actual needs; compared with the black-box-oriented confrontation sample generation method, the present invention not only does not destroy the original function of malware, but also has a high success rate in deceiving the malware classifier, The problem of not being able to balance the low success rate of adversarial sample deception and the broken malware function is greatly improved.

Description

technical field [0001] The invention relates to a malicious software countermeasure sample generation method combined with API fuzzy processing technology, and belongs to the technical field of computer and information science. Background technique [0002] Due to a large number of malware attacks in cyberspace, machine learning technology has been widely used in malware detection and classification. In order to evaluate the attack resistance of malware detection models, it is particularly important to study attack methods for malware detection models. At the same time, the deep model itself has been proven to be vulnerable to adversarial samples. So far, although adversarial learning has been an active research field, most of the research on adversarial samples is mostly applied in the field of image recognition. Adversarial attack methods for malware detection systems are in the minority, and most adversarial sample generation methods cannot guarantee the executability of ...

AI Technical Summary

Problems solved by technology

[0003] The basic problems to be solved in malware countermeasure generation methods are: generating irrelevant APIs to insert into the original API sequence, hiding imported API functions through an API obfuscation technique, and deceiving malware classifiers into misclassifications with a high success rate

But these methods usually break the functionality of the malware, resulting in the inability to create adversarial examples that can work effectively in practice.

[0008] To sum up, among the existing malware adversarial sample generation methods, the black-box-oriented attack method is more feasible, but it is difficult to guarantee that the malware function will not be destroyed after the disturbance is added, and that the adversarial samples can be used in real-world applications. counter attack

Images