mlsanityData to 14 Oct 2026

On the Robustness of Domain Constraints

arXiv 2105.08619 ↗First posted 18 May 2021cs.CR cs.LG cs.LOcited by 11

Not on the map. Why?

Abstract (arXiv)

Machine learning is vulnerable to adversarial examples-inputs designed to cause models to perform poorly. However, it is unclear if adversarial examples represent realistic inputs in the modeled domains. Diverse domains such as networks and phishing have domain constraints-complex relationships between features that an adversary must satisfy for an attack to be realized (in addition to any adversary-specific goals). In this paper, we explore how domain constraints limit adversarial capabilities and how adversaries can adapt their strategies to create realistic (constraint-compliant) examples. In this, we develop techniques to learn domain constraints from data, and show how the learned constraints can be integrated into the adversarial crafting process. We evaluate the efficacy of our approach in network intrusion and phishing datasets and find: (1) up to 82% of adversarial examples produced by state-of-the-art crafting algorithms violate domain constraints, (2) domain constraints are robust to adversarial examples; enforcing constraints yields an increase in model accuracy by up to 34%. We observe not only that adversaries must alter inputs to satisfy domain constraints, but that these constraints make the generation of valid adversarial examples far more challenging.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 35 of its 76 references that are in the map. First posted on arXiv 18 May 2021.

Builds on

35 of 76 references.

References · 35

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2013Intriguing properties of neural networkscited by 5,155
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  6. 2016Adversarial examples in the physical worldcited by 1,769
  7. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,055
  8. 2016Adversarial Machine Learning at Scalecited by 936
  9. 2016Practical Black-Box Attacks against Machine Learningcited by 903
  10. 2015The Limitations of Deep Learning in Adversarial Settingscited by 790
  11. 2017One pixel attack for fooling deep neural networkscited by 582
  12. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 567
23 more
  1. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 546
  2. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 536
  3. 2017Adversarial Patchcited by 517
  4. 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 501
  5. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 486
  6. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 462
  7. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 446
  8. 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 442
  9. 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 414
  10. 2018Certified Defenses against Adversarial Examplescited by 306
  11. 2017Certified Defenses for Data Poisoning Attackscited by 303
  12. 2018Audio Adversarial Examples: Targeted Attacks on Speech-to-Textcited by 274
  13. 2017Detecting Adversarial Samples from Artifactscited by 245
  14. 2017On the (Statistical) Detection of Adversarial Examplescited by 180
  15. 2017The Space of Transferable Adversarial Examplescited by 158
  16. 2016Crafting Adversarial Input Sequences for Recurrent Neural Networkscited by 103
  17. 2015Characterizing Concept Driftcited by 94
  18. 2017A General Framework for Adversarial Examples with Objectivescited by 84
  19. 2018Adversarial Malware Binaries: Evading Deep Learning for Malware Detection in Executablescited by 62
  20. 2018IDSGAN: Generative Adversarial Networks for Attack Generation against Intrusion Detectioncited by 42
  21. 2016Deep Learning in Financecited by 18
  22. 2020Adversarial Examples in Constrained Domainscited by 11
  23. 2019Rearchitecting Classification Frameworks For Increased Robustnesscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 3; 2023: 1; 2024: 2; 2025: 2; 2026: 1.

11 papers.

  1. 2022"Real Attackers Don't Compute Gradients": Bridging the Gap Between Adversarial ML Research and Practicecited by 56
  2. 2022On The Empirical Effectiveness of Unrealistic Adversarial Hardening Against Realistic Adversarial Attackscited by 15
  3. 2021SoK: Machine Learning Governancecited by 10
  4. 2023Poisoning Network Flow Classifierscited by 3
  5. 2024PASA: Attack Agnostic Unsupervised Adversarial Detection using Prediction & Attribution Sensitivity Analysiscited by 3
  6. 2022Level Up with ML Vulnerability Identification: Leveraging Domain Constraints in Feature Space for Robust Android Malware Detectioncited by 2
  7. 2021On the Exploitability of Audio Machine Learning Pipelines to Surreptitious Adversarial Examplescited by 1
  8. 2024Improving Adversarial Robustness in Android Malware Detection by Reducing the Impact of Spurious Correlationscited by 0
  9. 2025Insights on Adversarial Attacks for Tabular Machine Learning via a Systematic Literature Reviewcited by 0
  10. 2025An Investigation into the Performance of Non-Contrastive Self-Supervised Learning Methods for Network Intrusion Detectioncited by 0
  11. 2026Robust Conformal Intrusion Detection via Traffic-Aware Calibration and Attack-Orbit Invariancecited by 0