mlsanityData to 7 Oct 2026

Adversarial Examples that Fool both Computer Vision and Time-Limited Humans

arXiv 1802.08195 ↗First posted 22 Feb 2018cs.LG cs.CV q-bio.NCcited by 73

Not on the map. Why?

Abstract (arXiv)

Machine learning models are vulnerable to adversarial examples: small changes to images can cause computer vision models to make mistakes such as identifying a school bus as an ostrich. However, it is still an open question whether humans are prone to similar mistakes. Here, we address this question by leveraging recent techniques that transfer adversarial examples from computer vision models with known parameters and architecture to other models with unknown parameters and architecture, and by matching the initial processing of the human visual system. We find that adversarial examples that strongly transfer across computer vision models influence the classifications made by time-limited human observers.

Key facts. Cited by 73 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 15; 2023: 21; 2024: 11; 2025: 7; 2026: 6.

73 papers.

Sort:

By area:

  1. 2021Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical Worldcited by 127
  2. 2023FLIRT: Feedback Loop In-context Red Teamingcited by 81
  3. 2024Prover-Verifier Games improve legibility of LLM outputscited by 79
  4. 2021FCA: Learning a 3D Full-coverage Vehicle Camouflage for Multi-view Physical Adversarial Attackcited by 74
  5. 2023Visual Anagrams: Generating Multi-View Optical Illusions with Diffusion Modelscited by 46
  6. 2023Neither hype nor gloom do DNNs justicecited by 40
  7. 2024Adversarial Robustness Limits via Scaling-Law and Human-Alignment Studiescited by 38
  8. 2023Spatial-frequency channels, shape bias, and adversarial robustnesscited by 28
  9. 2024Factorized Diffusion: Perceptual Illusions by Noise Decompositioncited by 23
  10. 2023Summon a Demon and Bind it: A Grounded Theory of LLM Red Teamingcited by 20
  11. 2023Towards more Practical Threat Models in Artificial Intelligence Securitycited by 17
  12. 2021A Survey on AI Assurancecited by 16
38 more
  1. 2022Designing Perceptual Puzzles by Differentiating Probabilistic Programscited by 12
  2. 2024Ensemble everything everywhere: Multi-scale aggregation for adversarial robustnesscited by 12
  3. 2022Finding Biological Plausibility for Adversarially Robust Features via Metameric Taskscited by 11
  4. 2022Metaethical Perspectives on 'Benchmarking' AI Ethicscited by 11
  5. 2022Visual Adversarial Attacks and Defenses in the Physical World: A Surveycited by 11
  6. 2023Adversarial Examples Might be Avoidable: The Role of Data Concentration in Adversarial Robustnesscited by 11
  7. 2023Are Deep Neural Networks Adequate Behavioural Models of Human Visual Perception?cited by 10
  8. 2023Multi-scale Diffusion Denoised Smoothingcited by 9
  9. 2021PDPGD: Primal-Dual Proximal Gradient Descent Adversarial Attackcited by 8
  10. 2022Joint rotational invariance and adversarial training of a dual-stream Transformer yields state of the art Brain-Score for Area V4cited by 7
  11. 2023Adversarial alignment: Breaking the trade-off between the strength of an attack and its relevance to human perceptioncited by 7
  12. 2021Simple Transparent Adversarial Examplescited by 6
  13. 2023DeepSeaNet: Improving Underwater Object Detection using EfficientDetcited by 6
  14. 2023Robustified ANNs Reveal Wormholes Between Human Category Perceptscited by 6
  15. 2023Evaluating Concurrent Robustness of Language Models Across Diverse Challenge Setscited by 6
  16. 2023Adversarial Item Promotion on Visually-Aware Recommender Systems by Guided Diffusioncited by 5
  17. 2022Human Eyes Inspired Recurrent Neural Networks are More Robust Against Adversarial Noisescited by 4
  18. 2022Adversarially trained neural representations may already be as robust as corresponding biological neural representationscited by 4
  19. 2022Audit and Improve Robustness of Private Neural Networks on Encrypted Datacited by 4
  20. 2023Compensating for Sensing Failures via Delegation in Human-AI Hybrid Systemscited by 4
  21. 2024Embodied Active Defense: Leveraging Recurrent Feedback to Counter Adversarial Patchescited by 4
  22. 2021Human Imperceptible Attacks and Applications to Improve Fairnesscited by 3
  23. 2022Empirical Advocacy of Bio-inspired Models for Robust Image Recognitioncited by 3
  24. 2022DDDM: a Brain-Inspired Framework for Robust Classificationcited by 3
  25. 2024Optimizing Delegation in Collaborative Human-AI Hybrid Teamscited by 3
  26. 2021Energy Attack: On Transferring Adversarial Examplescited by 2
  27. 2021Two Souls in an Adversarial Image: Towards Universal Adversarial Example Detection using Multi-view Inconsistencycited by 2
  28. 2022Is current research on adversarial robustness addressing the right problem?cited by 2
  29. 2022Complexity of Representations in Deep Learningcited by 2
  30. 2022Multi-head Uncertainty Inference for Adversarial Attack Detectioncited by 2
  31. 2024Non-Uniform Illumination Attack for Fooling Convolutional Neural Networkscited by 2
  32. 2025PanoDiff-SR: Synthesizing Dental Panoramic Radiographs using Diffusion and Super-resolutioncited by 2
  33. 2021Bio-inspired Robustness: A Reviewcited by 1
  34. 2021Immuno-mimetic Deep Neural Networks (Immuno-Net)cited by 1
  35. 2021Data Efficient Human Intention Prediction: Leveraging Neural Network Verification and Expert Guidancecited by 1
  36. 2021Image classifiers can not be made robust to small perturbationscited by 1
  37. 2022Operationalizing Specifications, In Addition to Test Sets for Evaluating Constrained Generative Modelscited by 1
  38. 2023Beyond the limitations of any imaginable mechanism: large language models and psycholinguisticscited by 1

50 most cited of 73 All 73 (JSON)