# Generating End-to-End Adversarial Examples for Malware Classifiers Using Explainability

arXiv: https://arxiv.org/abs/2009.13243 · HTML: https://mlsanity.com/paper/2009.13243/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Sep 2020.

## Built on by (most cited first, 9 of 9)

- [Adversarial Attacks against Windows PE Malware Detection: A Survey of the State-of-the-Art](https://mlsanity.com/paper/2112.12310/) (2021)
- [Adversarial Robustness with Non-uniform Perturbations](https://mlsanity.com/paper/2102.12002/) (2021)
- [Impeding LLM-assisted Cheating in Introductory Programming Assignments via Adversarial Perturbation](https://mlsanity.com/paper/2410.09318/) (2024)
- [EG-Booster: Explanation-Guided Booster of ML Evasion Attacks](https://mlsanity.com/paper/2108.13930/) (2021)
- [The Power of MEME: Adversarial Malware Creation with Model-Based Reinforcement Learning](https://mlsanity.com/paper/2308.16562/) (2023)
- [Stealing and Evading Malware Classifiers and Antivirus at Low False Positive Conditions](https://mlsanity.com/paper/2204.06241/) (2022)
- [Analyzing the Impact of Adversarial Examples on Explainable Machine Learning](https://mlsanity.com/paper/2307.08327/) (2023)
- [Instance Attack:An Explanation-based Vulnerability Analysis Framework Against DNNs for Malware Detection](https://mlsanity.com/paper/2209.02453/) (2022)
- [Certifiably robust malware detectors by design](https://mlsanity.com/paper/2508.10038/) (2025)

## Abstract (arXiv)

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.