mlsanityData to 7 Oct 2026

Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images

arXiv 1412.1897 ↗First posted 5 Dec 2014cs.CV cs.AI cs.NEcited by 774

Not on the map. Why?

Cited by 21 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Deep neural networks (DNNs) have recently been achieving state-of-the-art performance on a variety of pattern-recognition tasks, most notably visual classification problems. Given that DNNs are now able to classify objects in images with near-human-level performance, questions naturally arise as to what differences remain between computer and human vision. A recent study revealed that changing an image (e.g. of a lion) in a way imperceptible to humans can cause a DNN to label the image as something else entirely (e.g. mislabeling a lion a library). Here we show a related result: it is easy to produce images that are completely unrecognizable to humans, but that state-of-the-art DNNs believe to be recognizable objects with 99.99% confidence (e.g. labeling with certainty that white noise static is a lion). Specifically, we take convolutional neural networks trained to perform well on either the ImageNet or MNIST datasets and then find images with evolutionary algorithms or gradient ascent that DNNs label with high confidence as belonging to each dataset class. It is possible to produce images totally unrecognizable to human eyes that DNNs believe with near certainty are familiar objects, which we call "fooling images" (more generally, fooling examples). Our results shed light on interesting differences between human vision and current DNNs, and raise questions about the generality of DNN computer vision.

Key facts. Cited by 774 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Dec 2014.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 171; 2022: 152; 2023: 156; 2024: 138; 2025: 97; 2026: 60.

774 papers.

Sort:

By area:

  1. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  2. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  3. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 596
  4. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  5. 2023The Curse of Recursion: Training on Generated Data Makes Models Forgetcited by 343
  6. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 338
  7. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 320
  8. 2022VOS: Learning What You Don't Know by Virtual Outlier Synthesiscited by 300
  9. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  10. 2022Mitigating Neural Network Overconfidence with Logit Normalizationcited by 251
  11. 2022Extremely Simple Activation Shaping for Out-of-Distribution Detectioncited by 212
  12. 2022Out-of-Distribution Detection and Selective Generation for Conditional Language Modelscited by 193
38 more
  1. 2021CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoderscited by 186
  2. 2021DICE: Leveraging Sparsification for Out-of-Distribution Detectioncited by 166
  3. 2023Image Hijacks: Adversarial Images can Control Generative Models at Runtimecited by 165
  4. 2026Towards End-to-End Automation of AI Researchcited by 150
  5. 2023Squeeze, Recover and Relabel: Dataset Condensation at ImageNet Scale From A New Perspectivecited by 136
  6. 2024iVideoGPT: Interactive VideoGPTs are Scalable World Modelscited by 136
  7. 2022Active Learning on a Budget: Opposite Strategies Suit High and Low Budgetscited by 131
  8. 2023CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say Nocited by 130
  9. 2023Non-Parametric Outlier Synthesiscited by 129
  10. 2022How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?cited by 128
  11. 2021Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunitiescited by 125
  12. 2021Salient ImageNet: How to discover spurious features in Deep Learning?cited by 114
  13. 2022POEM: Out-of-Distribution Detection with Posterior Samplingcited by 108
  14. 2021Can multi-label classification networks know what they don't know?cited by 100
  15. 2022Adversarial Texture for Fooling Person Detectors in the Physical Worldcited by 96
  16. 2021The effectiveness of feature attribution methods and its correlation with automatic evaluation scorescited by 87
  17. 2022Training OOD Detectors in their Natural Habitatscited by 86
  18. 2021Provable Guarantees for Understanding Out-of-distribution Detectioncited by 78
  19. 2023Dream the Impossible: Outlier Imagination with Diffusion Modelscited by 77
  20. 2022Variational Model Inversion Attackscited by 75
  21. 2021Does Your Dermatology Classifier Know What It Doesn't Know? Detecting the Long-Tail of Unseen Conditionscited by 68
  22. 2021On the Impact of Spurious Correlation for Out-of-distribution Detectioncited by 68
  23. 2022Calibrated Learning to Defer with One-vs-All Classifierscited by 68
  24. 2022RbA: Segmenting Unknown Regions Rejected by Allcited by 67
  25. 2021Understanding Softmax Confidence and Uncertaintycited by 62
  26. 2022Trustworthy clinical AI solutions: a unified review of uncertainty quantification in deep learning models for medical image analysiscited by 62
  27. 2022Hebbian Deep Learning Without Feedbackcited by 61
  28. 2022Rethinking Reconstruction Autoencoder-Based Out-of-Distribution Detectioncited by 59
  29. 2021Hierarchical VAEs Know What They Don't Knowcited by 58
  30. 2022Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attackscited by 58
  31. 2023When Does Confidence-Based Cascade Deferral Suffice?cited by 58
  32. 2022RankFeat: Rank-1 Feature Removal for Out-of-distribution Detectioncited by 52
  33. 2021Adversarial Example Detection for DNN Models: A Review and Experimental Comparisoncited by 51
  34. 2022A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awarenesscited by 49
  35. 2022Packed-Ensembles for Efficient Uncertainty Estimationcited by 49
  36. 2023Fast Decision Boundary based Out-of-Distribution Detectorcited by 48
  37. 2023Adversarial attacks and defenses in explainable artificial intelligence: A surveycited by 47
  38. 2021Energy-Based Open-World Uncertainty Modeling for Confidence Calibrationcited by 46

50 most cited of 774 All 774 (JSON)