mlsanityData to 7 Oct 2026

Boosting Adversarial Training with Hypersphere Embedding

arXiv 2002.08619 ↗First posted 20 Feb 2020cs.LG cs.CR cs.CVcited by 97

Not on the map. Why?

Abstract (arXiv)

Adversarial training (AT) is one of the most effective defenses against adversarial attacks for deep learning models. In this work, we advocate incorporating the hypersphere embedding (HE) mechanism into the AT procedure by regularizing the features onto compact manifolds, which constitutes a lightweight yet effective module to blend in the strength of representation learning. Our extensive analyses reveal that AT and HE are well coupled to benefit the robustness of the adversarially trained models from several aspects. We validate the effectiveness and adaptability of HE by embedding it into the popular AT frameworks including PGD-AT, ALP, and TRADES, as well as the FreeAT and FastAT strategies. In the experiments, we evaluate our methods under a wide range of adversarial attacks on the CIFAR-10 and ImageNet datasets, which verifies that integrating HE can consistently enhance the model robustness for each AT framework with little extra computation.

Key facts. Cited by 97 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 31; 2022: 24; 2023: 20; 2024: 13; 2025: 8; 2026: 1.

97 papers.

Sort:

By area:

  1. 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 276
  2. 2021Improving Robustness using Generated Datacited by 233
  3. 2023Better Diffusion Models Further Improve Adversarial Trainingcited by 207
  4. 2023Cross-Entropy Loss Functions: Theoretical Analysis and Applicationscited by 206
  5. 2021Fixing Data Augmentation to Improve Adversarial Robustnesscited by 201
  6. 2021Data Augmentation Can Improve Robustnesscited by 193
  7. 2021Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyondcited by 151
  8. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  9. 2022Robustness and Accuracy Could Be Reconcilable by (Proper) Definitioncited by 109
  10. 2022LAS-AT: Adversarial Training with Learnable Attack Strategycited by 94
  11. 2021Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networkscited by 73
  12. 2021Relating Adversarially Robust Generalization to Flat Minimacited by 57
38 more
  1. 2021Adversarial Robustness under Long-Tailed Distributioncited by 50
  2. 2022Practical Evaluation of Adversarial Robustness via Adaptive Auto Attackcited by 44
  3. 2021CausalAdv: Adversarial Robustness through the Lens of Causalitycited by 37
  4. 2022Prior-Guided Adversarial Initialization for Fast Adversarial Trainingcited by 34
  5. 2023Improving Fast Adversarial Training with Prior-Guided Knowledgecited by 34
  6. 2021Exploring Misclassifications of Robust Neural Networks to Enhance Adversarial Attackscited by 33
  7. 2021Analysis and Applications of Class-wise Robustness in Adversarial Trainingcited by 33
  8. 2022Enhancing Diffusion-Based Image Synthesis with Robust Classifier Guidancecited by 33
  9. 2022DISCO: Adversarial Defense with Local Implicit Functionscited by 33
  10. 2021Attacking Adversarial Attacks as A Defensecited by 31
  11. 2023Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectivescited by 30
  12. 2021Low Curvature Activations Reduce Overfitting in Adversarial Trainingcited by 29
  13. 2021A Review of Adversarial Attack and Defense for Classification Methodscited by 29
  14. 2022Robust Models are less Over-Confidentcited by 25
  15. 2021LAFEAT: Piercing Through Adversarial Defenses with Latent Featurescited by 24
  16. 2023Language-Driven Anchors for Zero-Shot Adversarial Robustnesscited by 23
  17. 2021Adaptive Image Transformations for Transfer-based Adversarial Attackcited by 22
  18. 2022CNN Filter DB: An Empirical Investigation of Trained Convolutional Filterscited by 20
  19. 2022Revisiting adapters with adversarial trainingcited by 18
  20. 2022Recognizing Object by Components with Human Prior Knowledge Enhances Adversarial Robustness of Deep Neural Networkscited by 18
  21. 2022Do Perceptually Aligned Gradients Imply Adversarial Robustness?cited by 15
  22. 2021Two Coupled Rejection Metrics Can Tell Adversarial Examples Apartcited by 14
  23. 2025PreGenie: An Agentic Framework for High-quality Visual Presentation Generationcited by 14
  24. 2021LTD: Low Temperature Distillation for Gradient Masking-free Adversarial Trainingcited by 13
  25. 2024Revisiting Adversarial Training under Long-Tailed Distributionscited by 13
  26. 2022Improving Robustness by Enhancing Weak Subnetscited by 12
  27. 2022Rethinking Bayesian Learning for Data Analysis: The Art of Prior and Inference in Sparsity-Aware Modelingcited by 12
  28. 2021Stochastic Local Winner-Takes-All Networks Enable Profound Adversarial Robustnesscited by 11
  29. 2022Diversified Adversarial Attacks based on Conjugate Gradient Methodcited by 11
  30. 2021Accumulative Poisoning Attacks on Real-time Datacited by 10
  31. 2021MixACM: Mixup-Based Robustness Transfer via Distillation of Activated Channel Mapscited by 9
  32. 2022Adversarial Robustness through the Lens of Convolutional Filterscited by 9
  33. 2022How many perturbations break this model? Evaluating robustness beyond adversarial accuracycited by 9
  34. 2023It Is All About Data: A Survey on the Effects of Data on Adversarial Robustnesscited by 9
  35. 2023Improving Adversarial Robust Fairness via Anti-Bias Soft Label Distillationcited by 8
  36. 2021Domain Invariant Adversarial Learningcited by 7
  37. 2023HateProof: Are Hateful Meme Detection Systems really Robust?cited by 7
  38. 2021Adaptive Perturbation for Adversarial Attackcited by 6

50 most cited of 97 All 97 (JSON)