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

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.

cs.CR cs.LG Computer Science Engineering

Source

Paper

References (19)

01Functionality-Preserving Black-Box Optimization of Adversarial Windows MalwareLuca Demetrio, B. Biggio, Giovanni Lagorio et al.2020 · IEEE Transactions on Information Forensics and Security · 181 citations In Library

02Malware Makeover: Breaking ML-based Static Analysis by Modifying Executable BytesKeane Lucas, Mahmood Sharif, Lujo Bauer et al.2019 · ACM Asia Conference on Computer and Communications Security · 92 citations In Library

03Deceiving End-to-End Deep Learning Malware Detectors using Adversarial ExamplesF. Kreuk, A. Barak, Shir Aviv-Reuven et al.2018 · 127 citations In Library

04Audio Adversarial Examples: Targeted Attacks on Speech-to-TextNicholas Carlini, D. Wagner2018 · 2018 IEEE Security and Privacy Workshops (SPW) · 1.2k citations In Library

05Wild Patterns: Ten Years After the Rise of Adversarial Machine LearningB. Biggio, F. Roli2017 · Pattern Recognition · 1.7k citations In Library

06Adversarial Examples for Malware DetectionKathrin Grosse, Nicolas Papernot, Praveen Manoharan et al.2017 · European Symposium on Research in Computer Security · 591 citations

07Yes, Machine Learning Can Be More Secure! A Case Study on Android Malware DetectionAmbra Demontis, Marco Melis, B. Biggio et al.2017 · IEEE Transactions on Dependable and Secure Computing · 307 citations In Library

08Intriguing properties of neural networksChristian Szegedy, Wojciech Zaremba, I. Sutskever et al.2013 · International Conference on Learning Representations · 17k citations In Library

09Evasion Attacks against Machine Learning at Test TimeB. Biggio, Igino Corona, Davide Maiorca et al.2013 · ECML/PKDD · 2.3k citations In Library

10Exploiting Machine Learning to Subvert Your Spam FilterB. Nelson, Marco Barreno, F. J. Chi et al.2008 · USENIX Workshop on Large-Scale Exploits and Emergent Threats · 398 citations

11Adversarial classificationNilesh N. Dalvi, Pedro M. Domingos, Mausam et al.2004 · Knowledge Discovery and Data Mining · 1.1k citations

12Adversarial EXEmples: A survey and experimental evaluation of practical attacks on machine learning for windows malware detection2021 · ACM Trans. Priv. Secur.

Scroll for more · 7 remaining