# Against All Odds: Winning the Defense Challenge in an Evasion Competition with Diversification

arXiv: https://arxiv.org/abs/2010.09569 · HTML: https://mlsanity.com/paper/2010.09569/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Oct 2020.

## Built on by (most cited first, 5 of 5)

- ["Real Attackers Don't Compute Gradients": Bridging the Gap Between Adversarial ML Research and Practice](https://mlsanity.com/paper/2212.14315/) (2022)
- [Adversarial Attacks against Windows PE Malware Detection: A Survey of the State-of-the-Art](https://mlsanity.com/paper/2112.12310/) (2021)
- [RS-Del: Edit Distance Robustness Certificates for Sequence Classifiers via Randomized Deletion](https://mlsanity.com/paper/2302.01757/) (2023)
- [A Comparison of Adversarial Learning Techniques for Malware Detection](https://mlsanity.com/paper/2308.09958/) (2023)
- [Machine Learning for Windows Malware Detection and Classification: Methods, Challenges and Ongoing Research](https://mlsanity.com/paper/2404.18541/) (2024)

## Abstract (arXiv)

Machine learning-based systems for malware detection operate in a hostile environment. Consequently, adversaries will also target the learning system and use evasion attacks to bypass the detection of malware. In this paper, we outline our learning-based system PEberus that got the first place in the defender challenge of the Microsoft Evasion Competition, resisting a variety of attacks from independent attackers. Our system combines multiple, diverse defenses: we address the semantic gap, use various classification models, and apply a stateful defense. This competition gives us the unique opportunity to examine evasion attacks under a realistic scenario. It also highlights that existing machine learning methods can be hardened against attacks by thoroughly analyzing the attack surface and implementing concepts from adversarial learning. Our defense can serve as an additional baseline in the future to strengthen the research on secure learning.