mlsanityData to 7 Oct 2026

Exploring Adversarial Examples in Malware Detection

arXiv 1810.08280 ↗First posted 18 Oct 2018cs.LG cs.CR stat.MLcited by 41

Not on the map. Why?

Abstract (arXiv)

The convolutional neural network (CNN) architecture is increasingly being applied to new domains, such as malware detection, where it is able to learn malicious behavior from raw bytes extracted from executables. These architectures reach impressive performance with no feature engineering effort involved, but their robustness against active attackers is yet to be understood. Such malware detectors could face a new attack vector in the form of adversarial interference with the classification model. Existing evasion attacks intended to cause misclassification on test-time instances, which have been extensively studied for image classifiers, are not applicable because of the input semantics that prevents arbitrary changes to the binaries. This paper explores the area of adversarial examples for malware detection. By training an existing model on a production-scale dataset, we show that some previous attacks are less effective than initially reported, while simultaneously highlighting architectural weaknesses that facilitate new attack strategies for malware classification. Finally, we explore how generalizable different attack strategies are, the trade-offs when aiming to increase their effectiveness, and the transferability of single-step attacks.

Key facts. Cited by 41 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Oct 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 5; 2023: 10; 2024: 7; 2025: 4; 2026: 4.

41 papers.

Sort:

By area:

  1. 2021Unsolved Problems in ML Safetycited by 291
  2. 2021The Threat of Offensive AI to Organizationscited by 37
  3. 2024Exploring the Deceptive Power of LLM-Generated Fake News: A Study of Real-World Detection Challengescited by 28
  4. 2021Adversarial Attacks against Windows PE Malware Detection: A Survey of the State-of-the-Artcited by 18
  5. 2023RS-Del: Edit Distance Robustness Certificates for Sequence Classifiers via Randomized Deletioncited by 17
  6. 2023A Survey on Malware Detection with Graph Representation Learningcited by 11
  7. 2023MalProtect: Stateful Defense Against Adversarial Query Attacks in ML-based Malware Detectioncited by 8
  8. 2021Turning Federated Learning Systems Into Covert Channelscited by 6
  9. 2021Explanation-Guided Diagnosis of Machine Learning Evasion Attackscited by 6
  10. 2022Efficient Malware Analysis Using Metric Embeddingscited by 6
  11. 2023Towards a Practical Defense against Adversarial Attacks on Deep Learning-based Malware Detectors via Randomized Smoothingcited by 5
  12. 2023A Comparison of Adversarial Learning Techniques for Malware Detectioncited by 5
29 more
  1. 2025Trace Gadgets: Minimizing Code Context for Machine Learning-Based Vulnerability Predictioncited by 5
  2. 2021Adversarial Attacks and Defenses for Social Network Text Processing Applications: Techniques, Challenges and Future Research Directionscited by 4
  3. 2021Single-Shot Black-Box Adversarial Attacks Against Malware Detectors: A Causal Language Model Approachcited by 4
  4. 2024A Robust Defense against Adversarial Attacks on Deep Learning-based Malware Detectors via (De)Randomized Smoothingcited by 4
  5. 2021Mal2GCN: A Robust Malware Detection Approach Using Deep Graph Convolutional Networks With Non-Negative Weightscited by 3
  6. 2022StratDef: Strategic Defense Against Adversarial Attacks in ML-based Malware Detectioncited by 3
  7. 2022Towards Efficient and Domain-Agnostic Evasion Attack with High-dimensional Categorical Inputscited by 3
  8. 2023DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustnesscited by 3
  9. 2023URET: Universal Robustness Evaluation Toolkit (for Evasion)cited by 3
  10. 2023Burning the Adversarial Bridges: Robust Windows Malware Detection Against Binary-level Mutationscited by 3
  11. 2021Evading Malware Classifiers via Monte Carlo Mutant Feature Discoverycited by 2
  12. 2023A Malware Classification Survey on Adversarial Attacks and Defencescited by 1
  13. 2024CARE: Ensemble Adversarial Robustness Evaluation Against Adaptive Attackers for Security Applicationscited by 1
  14. 2024Evading Deep Learning-Based Malware Detectors via Obfuscation: A Deep Reinforcement Learning Approachcited by 1
  15. 2024Machine Learning for Windows Malware Detection and Classification: Methods, Challenges and Ongoing Researchcited by 1
  16. 2025On the Security Risks of ML-based Malware Detection Systems: A Surveycited by 1
  17. 2021Who's Afraid of Thomas Bayes?cited by 0
  18. 2021A Comparison of State-of-the-Art Techniques for Generating Adversarial Malware Binariescited by 0
  19. 2022Instance Attack:An Explanation-based Vulnerability Analysis Framework Against DNNs for Malware Detectioncited by 0
  20. 2022Multi-view Representation Learning from Malware to Defend Against Adversarial Variantscited by 0
  21. 2023High-resolution Image-based Malware Classification using Multiple Instance Learningcited by 0
  22. 2024Certified Adversarial Robustness of Machine Learning-based Malware Detectors via (De)Randomized Smoothingcited by 0
  23. 2024On the Robustness of Malware Detectors to Adversarial Samplescited by 0
  24. 2025Certifiably robust malware detectors by designcited by 0
  25. 2025DeepProv: Behavioral Characterization and Repair of Neural Networks via Inference Provenance Graph Analysiscited by 0
  26. 2026Adversarial Co-Evolution of Malware and Detection Models: A Bilevel Optimization Perspectivecited by 0
  27. 2026Learning to Look Benign: Targeted Evasion of Malware Detectors via API Import Injectioncited by 0
  28. 2026Cost-Aware Hierarchical Multi-Agent Ransomware Detection and Family Attributioncited by 0
  29. 2026ALIBI: Adversarial Legitimacy Injection in Binary Input against LLM Malware Analyzerscited by 0