mlsanityData to 7 Oct 2026

Unrestricted Adversarial Examples

arXiv 1809.08352 ↗First posted 22 Sep 2018stat.ML cs.CV cs.LGcited by 40

Not on the map. Why?

Abstract (arXiv)

We introduce a two-player contest for evaluating the safety and robustness of machine learning systems, with a large prize pool. Unlike most prior work in ML robustness, which studies norm-constrained adversaries, we shift our focus to unconstrained adversaries. Defenders submit machine learning models, and try to achieve high accuracy and coverage on non-adversarial data while making no confident mistakes on adversarial inputs. Attackers try to subvert defenses by finding arbitrary unambiguous inputs where the model assigns an incorrect label with high confidence. We propose a simple unambiguous dataset ("bird-or- bicycle") to use as part of this contest. We hope this contest will help to more comprehensively evaluate the worst-case adversarial risk of machine learning models.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Sep 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 1; 2019: 0; 2020: 0; 2021: 7; 2022: 7; 2023: 9; 2024: 10; 2025: 4; 2026: 2.

40 papers.

Sort:

By area:

  1. 2018Scalable agent alignment via reward modeling: a research directioncited by 438
  2. 2023Automatically Auditing Large Language Models via Discrete Optimizationcited by 187
  3. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  4. 2024Defending Against Unforeseen Failure Modes with Latent Adversarial Trainingcited by 82
  5. 2022Adversarial Training for High-Stakes Reliabilitycited by 60
  6. 2023A Survey on Transferability of Adversarial Examples across Deep Neural Networkscited by 43
  7. 2024Reasoning Robustness of LLMs to Adversarial Typographical Errorscited by 31
  8. 2024Adversarial Attacks of Vision Tasks in the Past 10 Years: A Surveycited by 22
  9. 2021Robustness and Generalization via Generative Adversarial Trainingcited by 20
  10. 2022Attacking deep networks with surrogate-based adversarial black-box methods is easycited by 18
  11. 2022StyleFool: Fooling Video Classification Systems via Style Transfercited by 18
  12. 2022Unrestricted Black-box Adversarial Attack Using GAN with Limited Queriescited by 18
28 more
  1. 2022Towards Transferable Unrestricted Adversarial Examples with Minimum Changescited by 13
  2. 2023Semantic Adversarial Attacks via Diffusion Modelscited by 12
  3. 2022Holistic Adversarial Robustness of Deep Learning Modelscited by 11
  4. 2021Domain Invariant Adversarial Learningcited by 7
  5. 2024Rethinking Impersonation and Dodging Attacks on Face Recognition Systemscited by 7
  6. 2021Adversarial Attack by Limited Point Cloud Surface Modificationscited by 6
  7. 2024Jailbreak Defense in a Narrow Domain: Limitations of Existing Methods and a New Transcript-Classifier Approachcited by 6
  8. 2021Generating Unrestricted Adversarial Examples via Three Parameterscited by 5
  9. 2023Class-Conditioned Transformation for Enhanced Robust Image Classificationcited by 5
  10. 2023Adversarial Attacks and Defenses on 3D Point Cloud Classification: A Surveycited by 5
  11. 2025NatADiff: Adversarial Boundary Guidance for Natural Adversarial Diffusioncited by 5
  12. 2024Adversarial Attacks on Both Face Recognition and Face Anti-spoofing Modelscited by 4
  13. 2021Tiny Adversarial Mulit-Objective Oneshot Neural Architecture Searchcited by 3
  14. 2023You Don't Need Robust Machine Learning to Manage Adversarial Attack Riskscited by 3
  15. 2023Turn Fake into Real: Adversarial Head Turn Attacks Against Deepfake Detectioncited by 3
  16. 2024A Random Ensemble of Encrypted Vision Transformers for Adversarially Robust Defensecited by 3
  17. 2024Improving the Transferability of Adversarial Attacks on Face Recognition with Diverse Parameters Augmentationcited by 3
  18. 2021An Adversarially-Learned Turing Test for Dialog Generation Modelscited by 2
  19. 2024SCA: Improve Semantic Consistent in Unrestricted Adversarial Attacks via DDPM Inversioncited by 2
  20. 2023Efficient Key-Based Adversarial Defense for ImageNet by Using Pre-trained Modelcited by 1
  21. 2024Sparse and Transferable Universal Singular Vectors Attackcited by 1
  22. 2025SCOOTER: A Human Evaluation Framework for Unrestricted Adversarial Examplescited by 1
  23. 2022Unrestricted Adversarial Samples Based on Non-semantic Feature Clusters Substitutioncited by 0
  24. 2023On the Computational Entanglement of Distant Features in Adversarial Machine Learningcited by 0
  25. 2025Countering Overfitting with Counterfactual Examplescited by 0
  26. 2025Generalizability vs. Counterfactual Explainability Trade-Offcited by 0
  27. 2026Exploiting Neural Audio Codec Latents for Adversarial Audio Attackscited by 0
  28. 2026Let the Carrier Carry the Attack: Preserving the Subject in Adversarial Image Generationcited by 0