Explanation-Guided Backdoor Poisoning Attacks Against Malware Classifiers
Published in
USENIX Security Symposium(2020)External Links:
TL
TL;DR
This paper proposes the use of techniques from explainable machine learning to guide the selection of relevant features and values to create effective backdoor triggers in a model-agnostic fashion, and demonstrates effective attacks against a diverse set of machine learning models.