@article{david_2022, 
  title={Generating End-to-End Adversarial Examples for Malware Classifiers Using   Explainability}, 
  abstractNote={In recent years, the topic of explainable machine learning (ML) has been
extensively researched. Up until now, this research focused on regular ML users
use-cases such as debugging a ML model. This paper takes a different posture
and show that adversaries can leverage explainable ML to bypass multi-feature
types malware classifiers. Previous adversarial attacks against such
classifiers only add new features and not modify existing ones to avoid harming
the modified malware executable's functionality. Current attacks use a single
algorithm that both selects which features to modify and modifies them blindly,
treating all features the same. In this paper, we present a different approach.
We split the adversarial example generation task into two parts: First we find
the importance of all features for a specific sample using explainability
algorithms, and then we conduct a feature-specific modification,
feature-by-feature. In order to apply our attack in black-box scenarios, we
introduce the concept of transferability of explainability, that is, applying
explainability algorithms to different classifiers using different features
subsets and trained on different datasets still result in a similar subset of
important features. We conclude that explainability algorithms can be leveraged
by adversaries and thus the advocates of training more interpretable
classifiers should consider the trade-off of higher vulnerability of those
classifiers to adversarial attacks.}, 
  author={David}, 
  year={2022}, 
  month={Jun}
  }