Practical Attacks on Machine Learning: A Case Study on Adversarial Windows Malware

07/12/2022

∙

While machine learning is vulnerable to adversarial examples, it still lacks systematic procedures and tools for evaluating its security in different application contexts. In this article, we discuss how to develop automated and scalable security evaluations of machine learning using practical attacks, reporting a use case on Windows malware detection.

READ FULL TEXT

Practical Attacks on Machine Learning: A Case Study on Adversarial Windows Malware

A survey on practical adversarial examples for malware classifiers

Adversarial Attacks against Windows PE Malware Detection: A Survey of the State-of-the-Art

secml-malware: A Python Library for Adversarial Robustness Evaluation of Windows Malware Classifiers

Greenhouse gases emissions: estimating corporate non-reported emissions using interpretable machine learning

A Comparison of Adversarial Learning Techniques for Malware Detection

Adversarial EXEmples: A Survey and Experimental Evaluation of Practical Attacks on Machine Learning for Windows Malware Detection

amsqr at MLSEC-2021: Thwarting Adversarial Malware Evasion with a Defense-in-Depth

Practical Attacks on Machine Learning: A Case Study on Adversarial Windows Malware

Related Research

A survey on practical adversarial examples for malware classifiers

Adversarial Attacks against Windows PE Malware Detection: A Survey of the State-of-the-Art

secml-malware: A Python Library for Adversarial Robustness Evaluation of Windows Malware Classifiers

Greenhouse gases emissions: estimating corporate non-reported emissions using interpretable machine learning

A Comparison of Adversarial Learning Techniques for Malware Detection

Adversarial EXEmples: A Survey and Experimental Evaluation of Practical Attacks on Machine Learning for Windows Malware Detection

amsqr at MLSEC-2021: Thwarting Adversarial Malware Evasion with a Defense-in-Depth