Query-Efficient Black-Box Attack Against Sequence-Based Malware Classifiers

TL;DR

This paper introduces a novel, query-efficient black-box attack method targeting sequence-based malware classifiers, achieving high success rates with minimal queries and limited knowledge of the model.

Contribution

It presents a new attack approach that reduces query count and knowledge requirements, outperforming existing methods in attacking malware classifiers.

Findings

Achieves 98% success rate with known confidence scores.

Achieves 64% success rate with only predicted class knowledge.

Requires fewer queries than previous attacks.

Abstract

In this paper, we present a generic, query-efficient black-box attack against API call-based machine learning malware classifiers. We generate adversarial examples by modifying the malware's API call sequences and non-sequential features (printable strings), and these adversarial examples will be misclassified by the target malware classifier without affecting the malware's functionality. In contrast to previous studies, our attack minimizes the number of malware classifier queries required. In addition, in our attack, the attacker must only know the class predicted by the malware classifier; attacker knowledge of the malware classifier's confidence score is optional. We evaluate the attack effectiveness when attacks are performed against a variety of malware classifier architectures, including recurrent neural network (RNN) variants, deep neural networks, support vector machines, and gradient boosted decision trees. Our attack success rate is around 98% when the classifier's confidence score is known and 64% when just the classifier's predicted class is known. We implement four state-of-the-art query-efficient attacks and show that our attack requires fewer queries and less knowledge about the attacked model's architecture than other existing query-efficient attacks, making it practical for attacking cloud-based malware classifiers at a minimal cost.