mlsanityData to 7 Oct 2026

Creating Valid Adversarial Examples of Malware

arXiv 2306.13587 ↗First posted 23 Jun 2023cs.CR cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

Machine learning is becoming increasingly popular as a go-to approach for many tasks due to its world-class results. As a result, antivirus developers are incorporating machine learning models into their products. While these models improve malware detection capabilities, they also carry the disadvantage of being susceptible to adversarial attacks. Although this vulnerability has been demonstrated for many models in white-box settings, a black-box attack is more applicable in practice for the domain of malware detection. We present a generator of adversarial malware examples using reinforcement learning algorithms. The reinforcement learning agents utilize a set of functionality-preserving modifications, thus creating valid adversarial examples. Using the proximal policy optimization (PPO) algorithm, we achieved an evasion rate of 53.84% against the gradient-boosted decision tree (GBDT) model. The PPO agent previously trained against the GBDT classifier scored an evasion rate of 11.41% against the neural network-based classifier MalConv and an average evasion rate of 2.31% against top antivirus programs. Furthermore, we discovered that random application of our functionality-preserving portable executable modifications successfully evades leading antivirus engines, with an average evasion rate of 11.65%. These findings indicate that machine learning-based models used in malware detection systems are vulnerable to adversarial attacks and that better safeguards need to be taken to protect these systems.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 19 of its 40 references that are in the map. First posted on arXiv 23 Jun 2023.

Builds on

19 of 40 references.

References · 19

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  4. 2016OpenAI Gymcited by 1,684
  5. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
  6. 2018EMBER: An Open Dataset for Training Static PE Malware Machine Learning Modelscited by 164
  7. 2017Malware Detection by Eating a Whole EXEcited by 114
  8. 2017Generating Adversarial Malware Examples for Black-Box Attacks Based on GANcited by 74
  9. 2018Learning to Evade Static PE Machine Learning Malware Models via Reinforcement Learningcited by 60
  10. 2018Adversarial Malware Binaries: Evading Deep Learning for Malware Detection in Executablescited by 60
  11. 2020Functionality-preserving Black-box Optimization of Adversarial Windows Malwarecited by 58
  12. 2017RLlib: Abstractions for Distributed Reinforcement Learningcited by 53
7 more
  1. 2017Survey of Machine Learning Techniques for Malware Analysiscited by 31
  2. 2019Explaining Vulnerabilities of Deep Learning to Adversarial Malware Binariescited by 30
  3. 2018Deceiving End-to-End Deep Learning Malware Detectors using Adversarial Examplescited by 19
  4. 2017Automated Poisoning Attacks and Defenses in Malware Detection Systems: An Adversarial Machine Learning Approachcited by 18
  5. 2022A Comparison of Static, Dynamic, and Hybrid Analysis for Malware Detectioncited by 16
  6. 2020Binary Black-box Evasion Attacks Against Deep Learning-based Static Malware Detectors with Adversarial Byte-Level Language Modelcited by 10
  7. 2022MERLIN -- Malware Evasion with Reinforcement LearnINgcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Adversarial Co-Evolution of Malware and Detection Models: A Bilevel Optimization Perspectivecited by 0
  2. 2026Adversarial Malware Generation in Linux ELF Binaries via Semantic-Preserving Transformationscited by 0
  3. 2026Building an Adversarial Malware Dataset by Family and Type: Generation, Evasion, and Poisoning Evaluationcited by 0