mlsanityData to 7 Oct 2026

Metric Learning for Adversarial Robustness

arXiv 1909.00900 ↗First posted 3 Sep 2019cs.LG cs.CR cs.CVcited by 77

Not on the map. Why?

Abstract (arXiv)

Deep networks are well-known to be fragile to adversarial attacks. We conduct an empirical analysis of deep representations under the state-of-the-art attack method called PGD, and find that the attack causes the internal representation to shift closer to the "false" class. Motivated by this observation, we propose to regularize the representation space under attack with metric learning to produce more robust classifiers. By carefully sampling examples for metric learning, our learned representation not only increases robustness, but also detects previously unseen adversarial samples. Quantitative experiments show improvement of robustness accuracy by up to 4% and detection efficiency by up to 6% according to Area Under Curve score over prior work. The code of our work is available at https://github.com/columbia/Metric_Learning_Adversarial_Robustness.

Key facts. Cited by 77 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 22; 2022: 21; 2023: 21; 2024: 10; 2025: 2; 2026: 1.

77 papers.

Sort:

By area:

  1. 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 276
  2. 2023Better Diffusion Models Further Improve Adversarial Trainingcited by 207
  3. 2024Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Modelscited by 119
  4. 2022Understanding Zero-Shot Adversarial Robustness for Large-Scale Modelscited by 117
  5. 2023How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defensescited by 65
  6. 2021Exploring Memorization in Adversarial Trainingcited by 55
  7. 2021Adversarial Robustness under Long-Tailed Distributioncited by 50
  8. 2021Adversarial Attacks are Reversible with Natural Supervisioncited by 47
  9. 2021Online Adversarial Purification based on Self-Supervisioncited by 45
  10. 2022A Survey of Robust Adversarial Training in Pattern Recognition: Fundamental, Theory, and Methodologiescited by 44
  11. 2022Enhancing Adversarial Training with Second-Order Statistics of Weightscited by 42
  12. 2022Multi-Objective Hyperparameter Optimization in Machine Learning -- An Overviewcited by 37
38 more
  1. 2022DISCO: Adversarial Defense with Local Implicit Functionscited by 33
  2. 2023Randomized Adversarial Training via Taylor Expansioncited by 28
  3. 2023Language-Driven Anchors for Zero-Shot Adversarial Robustnesscited by 23
  4. 2022The Enemy of My Enemy is My Friend: Exploring Inverse Adversaries for Improving Adversarial Trainingcited by 22
  5. 2021SPADE: A Spectral Method for Black-Box Adversarial Robustness Evaluationcited by 16
  6. 2022Landscape Learning for Neural Network Inversioncited by 15
  7. 2021Two Coupled Rejection Metrics Can Tell Adversarial Examples Apartcited by 14
  8. 2024Does Negative Sampling Matter? A Review with Insights into its Theory and Applicationscited by 14
  9. 2024Preventing Catastrophic Overfitting in Fast Adversarial Training: A Bi-level Optimization Perspectivecited by 12
  10. 2024I Can Hear You: Selective Robust Training for Deepfake Audio Detectioncited by 12
  11. 2023Robust Nonparametric Regression under Poisoning Attackcited by 11
  12. 2021AGKD-BML: Defense Against Adversarial Attack by Attention Guided Knowledge Distillation and Bi-directional Metric Learningcited by 10
  13. 2021Improving Model Robustness by Adaptively Correcting Perturbation Levels with Active Queriescited by 9
  14. 2021Improving Model Robustness with Latent Distribution Locally and Globallycited by 9
  15. 2021MixACM: Mixup-Based Robustness Transfer via Distillation of Activated Channel Mapscited by 9
  16. 2022Spectral, Probabilistic, and Deep Metric Learning: Tutorial and Surveycited by 9
  17. 2022Robust Perception through Equivariancecited by 9
  18. 2021Understanding and Achieving Efficient Robustness with Adversarial Supervised Contrastive Learningcited by 8
  19. 2022A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunitiescited by 8
  20. 2023Defense against Adversarial Cloud Attack on Remote Sensing Salient Object Detectioncited by 8
  21. 2024Machine Learning Robustness: A Primercited by 8
  22. 2021Real-Time Neural Voice Camouflagecited by 6
  23. 2022A Tale of Two Models: Constructing Evasive Attacks on Edge Modelscited by 6
  24. 2022Improving Adversarial Robustness with Self-Paced Hard-Class Pair Reweightingcited by 6
  25. 2023Adversarial Finetuning with Latent Representation Constraint to Mitigate Accuracy-Robustness Tradeoffcited by 6
  26. 2023Adversarial Attacks and Defenses in Machine Learning-Powered Networks: A Contemporary Surveycited by 5
  27. 2021Exploring Adversarial Robustness of Deep Metric Learningcited by 4
  28. 2021Adversarially Robust Kernel Smoothingcited by 4
  29. 2023Test-time Detection and Repair of Adversarial Samples via Masked Autoencodercited by 4
  30. 2023Exploring Robust Features for Improving Adversarial Robustnesscited by 4
  31. 2024Exploring Adversarial Robustness of Deep State Space Modelscited by 4
  32. 2021Model-Agnostic Meta-Attack: Towards Reliable Evaluation of Adversarial Robustnesscited by 3
  33. 2022What Do Adversarially trained Neural Networks Focus: A Fourier Domain-based Studycited by 3
  34. 2023Enhance Diffusion to Improve Robust Generalizationcited by 3
  35. 2023Robust Proxy: Improving Adversarial Robustness by Robust Proxy Learningcited by 3
  36. 2024Learning Robust and Privacy-Preserving Representations via Information Theorycited by 3
  37. 2021Deep Repulsive Prototypes for Adversarial Robustnesscited by 2
  38. 2022Dual Graphs of Polyhedral Decompositions for the Detection of Adversarial Attackscited by 2

50 most cited of 77 All 77 (JSON)