ATMPA: Attacking Machine Learning-based Malware Visualization Detection Methods via Adversarial Examples
arXiv:1808.01546
Abstract
Since the threat of malicious software (malware) has become increasingly serious, automatic malware detection techniques have received increasing attention, where machine learning (ML)-based visualization detection methods become more and more popular. In this paper, we demonstrate that the state-of-the-art ML-based visualization detection methods are vulnerable to Adversarial Example (AE) attacks. We develop a novel Adversarial Texture Malware Perturbation Attack (ATMPA) method based on the gradient descent and L-norm optimization method, where attackers can introduce some tiny perturbations on the transformed dataset such that ML-based malware detection methods will completely fail. The experimental results on the MS BIG malware dataset show that a small interference can reduce the accuracy rate down to 0% for several ML-based detection methods, and the rate of transferability is 74.1% on average.
arXiv comment9 pages, 5 figures
References in corpus (12)
- Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
- Microsoft Malware Classification Challenge
- Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients
- Adversarial Examples: Opportunities and Challenges
- Adversarial Examples: Attacks and Defenses for Deep Learning
- Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey
- Detecting and Classifying Android Malware using Static Analysis along with Creator Information
- MagNet and "Efficient Defenses Against Adversarial Attacks" are Not Robust to Adversarial Examples
- Black-Box Attacks against RNN based Malware Detection Algorithms
- Generative Adversarial Trainer: Defense to Adversarial Perturbations with GAN
- Adversarial Deep Learning for Robust Detection of Binary Encoded Malware
- Defense against Universal Adversarial Perturbations