# MAB-Malware: A Reinforcement Learning Framework for Attacking Static Malware Classifiers

arXiv: https://arxiv.org/abs/2003.03100 · HTML: https://mlsanity.com/paper/2003.03100/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Mar 2020.

## Built on by (most cited first, 8 of 8)

- [Adversarial Attacks against Windows PE Malware Detection: A Survey of the State-of-the-Art](https://mlsanity.com/paper/2112.12310/) (2021)
- [EvadeDroid: A Practical Evasion Attack on Machine Learning for Black-box Android Malware Detection](https://mlsanity.com/paper/2110.03301/) (2021)
- [Evading Malware Classifiers via Monte Carlo Mutant Feature Discovery](https://mlsanity.com/paper/2106.07860/) (2021)
- [Towards interpreting ML-based automated malware detection models: a survey](https://mlsanity.com/paper/2101.06232/) (2021)
- [Instance Attack:An Explanation-based Vulnerability Analysis Framework Against DNNs for Malware Detection](https://mlsanity.com/paper/2209.02453/) (2022)
- [EGAN: Evolutional GAN for Ransomware Evasion](https://mlsanity.com/paper/2405.12266/) (2024)
- [Adversarial Co-Evolution of Malware and Detection Models: A Bilevel Optimization Perspective](https://mlsanity.com/paper/2604.22569/) (2026)
- [Gray-Box Poisoning of Continuous Malware Ingestion Pipelines](https://mlsanity.com/paper/2605.04698/) (2026)

## Abstract (arXiv)

Modern commercial antivirus systems increasingly rely on machine learning to keep up with the rampant inflation of new malware. However, it is well-known that machine learning models are vulnerable to adversarial examples (AEs). Previous works have shown that ML malware classifiers are fragile to the white-box adversarial attacks. However, ML models used in commercial antivirus products are usually not available to attackers and only return hard classification labels. Therefore, it is more practical to evaluate the robustness of ML models and real-world AVs in a pure black-box manner. We propose a black-box Reinforcement Learning (RL) based framework to generate AEs for PE malware classifiers and AV engines. It regards the adversarial attack problem as a multi-armed bandit problem, which finds an optimal balance between exploiting the successful patterns and exploring more varieties. Compared to other frameworks, our improvements lie in three points. 1) Limiting the exploration space by modeling the generation process as a stateless process to avoid combination explosions. 2) Due to the critical role of payload in AE generation, we design to reuse the successful payload in modeling. 3) Minimizing the changes on AE samples to correctly assign the rewards in RL learning. It also helps identify the root cause of evasions. As a result, our framework has much higher black-box evasion rates than other off-the-shelf frameworks. Results show it has over 74%--97% evasion rate for two state-of-the-art ML detectors and over 32%--48% evasion rate for commercial AVs in a pure black-box setting. We also demonstrate that the transferability of adversarial attacks among ML-based classifiers is higher than the attack transferability between purely ML-based and commercial AVs.