mlsanityData to 14 Oct 2026

Latent Feature Relation Consistency for Adversarial Robustness

arXiv 2303.16697 ↗First posted 29 Mar 2023cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Deep neural networks have been applied in many computer vision tasks and achieved state-of-the-art performance. However, misclassification will occur when DNN predicts adversarial examples which add human-imperceptible adversarial noise to natural examples. This limits the application of DNN in security-critical fields. To alleviate this problem, we first conducted an empirical analysis of the latent features of both adversarial and natural examples and found the similarity matrix of natural examples is more compact than those of adversarial examples. Motivated by this observation, we propose Latent Feature Relation Consistency (LFRC), which constrains the relation of adversarial examples in latent space to be consistent with the natural examples. Importantly, our LFRC is orthogonal to the previous method and can be easily combined with them to achieve further improvement. To demonstrate the effectiveness of LFRC, we conduct extensive experiments using different neural networks on benchmark datasets. For instance, LFRC can bring 0.78% further improvement compared to AT, and 1.09% improvement compared to TRADES, against AutoAttack on CIFAR10. Code is available at https://github.com/liuxingbin/LFRC.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 26 of its 35 references that are in the map. First posted on arXiv 29 Mar 2023.

Builds on

26 of 35 references.

References · 26

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  5. 2016Wide Residual Networkscited by 3,070
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  7. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
  8. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  9. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 685
  10. 2020BERT-ATTACK: Adversarial Attack Against BERT Using BERTcited by 491
  11. 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 442
  12. 2019Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attackscited by 355
14 more
  1. 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 334
  2. 2018Feature Denoising for Improving Adversarial Robustnesscited by 314
  3. 2018Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionalitycited by 282
  4. 2018Adversarial Logit Pairingcited by 224
  5. 2018Adversarial Risk and the Dangers of Evaluating Against Weak Attackscited by 221
  6. 2020Geometry-aware Instance-reweighted Adversarial Trainingcited by 198
  7. 2020A Self-supervised Approach for Adversarial Robustnesscited by 180
  8. 2020Robust Pre-Training by Adversarial Contrastive Learningcited by 144
  9. 2020Adversarial Self-Supervised Contrastive Learningcited by 139
  10. 2019Model-free Deep Reinforcement Learning for Urban Autonomous Drivingcited by 98
  11. 2019Defensive Quantization: When Efficiency Meets Robustnesscited by 95
  12. 2020Transferable, Controllable, and Inconspicuous Adversarial Attacks on Person Re-identification With Deep Mis-Rankingcited by 42
  13. 2021Reliably fast adversarial training via latent adversarial perturbationcited by 29
  14. 2021Local Reweighting for Adversarial Trainingcited by 1

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024Black-Box Access is Insufficient for Rigorous AI Auditscited by 126