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

Luca Demetrio, Battista Biggio, Fabio Roli

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