Generic Black-Box End-to-End Attack Against State of the Art API Call Based Malware Classifiers
This addresses a security vulnerability for malware detection systems, presenting a black-box attack that can bypass state-of-the-art classifiers, which is incremental as it builds on existing adversarial attack principles.
The paper tackles the problem of evading malware classifiers by generating adversarial sequences that combine API calls and static features to cause misclassification without affecting malware functionality, showing effectiveness against various classifiers including RNNs, DNNs, and SVMs due to transferability.
In this paper, we present a black-box attack against API call based machine learning malware classifiers, focusing on generating adversarial sequences combining API calls and static features (e.g., printable strings) that will be misclassified by the classifier without affecting the malware functionality. We show that this attack is effective against many classifiers due to the transferability principle between RNN variants, feed forward DNNs, and traditional machine learning classifiers such as SVM. We also implement GADGET, a software framework to convert any malware binary to a binary undetected by malware classifiers, using the proposed attack, without access to the malware source code.