mlsanityData to 7 Oct 2026

LAFEAT: Piercing Through Adversarial Defenses with Latent Features

arXiv 2104.09284 ↗First posted 19 Apr 2021cs.LG cs.CVcited by 24

Not on the map. Why?

Abstract (arXiv)

Deep convolutional neural networks are susceptible to adversarial attacks. They can be easily deceived to give an incorrect output by adding a tiny perturbation to the input. This presents a great challenge in making CNNs robust against such attacks. An influx of new defense techniques have been proposed to this end. In this paper, we show that latent features in certain "robust" models are surprisingly susceptible to adversarial attacks. On top of this, we introduce a unified ℓ_∞-norm white-box attack algorithm which harnesses latent features in its gradient descent steps, namely LAFEAT. We show that not only is it computationally much more efficient for successful attacks, but it is also a stronger adversary than the current state-of-the-art across a wide range of defense mechanisms. This suggests that model robustness could be contingent on the effective use of the defender's hidden components, and it should no longer be viewed from a holistic perspective.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Builds on 41 of its 63 references that are in the map. First posted on arXiv 19 Apr 2021.

Builds on

41 of 63 references.

References · 41

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  6. 2016Adversarial examples in the physical worldcited by 1,762
  7. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  8. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  9. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  10. 2016Adversarial Machine Learning at Scalecited by 934
  11. 2020Fast is better than free: Revisiting adversarial trainingcited by 723
  12. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
29 more
  1. 2019Adversarial Training for Free!cited by 638
  2. 2017One pixel attack for fooling deep neural networkscited by 579
  3. 2020Overfitting in adversarially robust deep learningcited by 504
  4. 2019On Evaluating Adversarial Robustnesscited by 442
  5. 2019Unlabeled Data Improves Adversarial Robustnesscited by 415
  6. 2019Using Pre-Training Can Improve Model Robustness and Uncertaintycited by 373
  7. 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 333
  8. 2020Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examplescited by 275
  9. 2018Generating Adversarial Examples with Adversarial Networkscited by 256
  10. 2020Bag of Tricks for Adversarial Trainingcited by 199
  11. 2019You Only Propagate Once: Accelerating Adversarial Training via Maximal Principlecited by 181
  12. 2018MMA Training: Direct Input Space Margin Maximization through Adversarial Trainingcited by 171
  13. 2019Stereo R-CNN based 3D Object Detection for Autonomous Drivingcited by 163
  14. 2019Are Labels Required for Improving Adversarial Robustness?cited by 162
  15. 2020Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuningcited by 152
  16. 2019End-to-End Model-Free Reinforcement Learning for Urban Driving using Implicit Affordancescited by 147
  17. 2019Adversarial Robustness through Local Linearizationcited by 146
  18. 2020Self-Adaptive Training: beyond Empirical Risk Minimizationcited by 126
  19. 2017Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuningcited by 110
  20. 2019Adversarial Robustness vs Model Compression, or Both?cited by 98
  21. 2020Boosting Adversarial Training with Hypersphere Embeddingcited by 97
  22. 2019Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Trainingcited by 95
  23. 2019Controlling Neural Level Setscited by 76
  24. 2019Adversarial Defense by Restricting the Hidden Space of Deep Neural Networkscited by 56
  25. 2017Art of singular vectors and universal adversarial perturbationscited by 49
  26. 2019An Alternative Surrogate Loss for PGD-based Adversarial Testingcited by 45
  27. 2019Harnessing the Vulnerability of Latent Layers in Adversarially Trained Modelscited by 26
  28. 2019AdvGAN++ : Harnessing latent layers for adversary generationcited by 20
  29. 2020Stylized Adversarial Defensecited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 6; 2023: 4; 2024: 2; 2025: 7; 2026: 1.

24 papers.

Sort:

By area:

  1. 2023Certifying LLM Safety against Adversarial Promptingcited by 248
  2. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  3. 2025Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agentscited by 112
  4. 2022Practical Evaluation of Adversarial Robustness via Adaptive Auto Attackcited by 44
  5. 2023Learning the Unlearnable: Adversarial Augmentations Suppress Unlearnable Example Attackscited by 28
  6. 2025MTL-UE: Learning to Learn Nothing for Multi-Task Learningcited by 11
  7. 2022Enhancing Adversarial Robustness for Deep Metric Learningcited by 10
  8. 2021Adversarial Attack and Defense in Deep Rankingcited by 8
  9. 2022MORA: Improving Ensemble Robustness Evaluation with Model-Reweighing Attackcited by 7
  10. 2024Exploring Privacy and Fairness Risks in Sharing Diffusion Models: An Adversarial Perspectivecited by 6
  11. 2023Adversarial Attacks and Defenses in Machine Learning-Powered Networks: A Contemporary Surveycited by 5
  12. 2025Beyond Vulnerabilities: A Survey of Adversarial Attacks as Both Threats and Defenses in Computer Vision Systemscited by 4
12 more
  1. 2021Adversarial Attacks on ML Defense Models Competitioncited by 3
  2. 2024Towards Million-Scale Adversarial Robustness Evaluation With Stronger Individual Attackscited by 3
  3. 2022Adversarial Attack and Defense for Non-Parametric Two-Sample Testscited by 2
  4. 2022Alternating Objectives Generates Stronger PGD-Based Adversarial Attackscited by 2
  5. 2025An h-space Based Adversarial Attack for Protection Against Few-shot Personalizationcited by 2
  6. 2025Towards Scalable Topological Regularizerscited by 1
  7. 2025Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Losscited by 1
  8. 2025RCR-AF: Enhancing Model Generalization via Rademacher Complexity Reduction Activation Functioncited by 1
  9. 2021Adversarial Robustness of Deep Reinforcement Learning based Dynamic Recommender Systemscited by 0
  10. 2022Towards Effective Multi-Label Recognition Attacks via Knowledge Graph Consistencycited by 0
  11. 2023On the Adversarial Robustness of Generative Autoencoders in the Latent Spacecited by 0
  12. 2026Dummy-Aware Weighted Attack (DAWA): Breaking the Safe Sink in Dummy Class Defensescited by 0