mlsanityData to 7 Oct 2026

Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Training

arXiv 1907.10764 ↗First posted 24 Jul 2019cs.CV cs.CR cs.LGcited by 95

Not on the map. Why?

Abstract (arXiv)

We introduce a feature scattering-based adversarial training approach for improving model robustness against adversarial attacks. Conventional adversarial training approaches leverage a supervised scheme (either targeted or non-targeted) in generating attacks for training, which typically suffer from issues such as label leaking as noted in recent works. Differently, the proposed approach generates adversarial images for training through feature scattering in the latent space, which is unsupervised in nature and avoids label leaking. More importantly, this new approach generates perturbed images in a collaborative fashion, taking the inter-sample relationships into consideration. We conduct analysis on model robustness and demonstrate the effectiveness of the proposed approach through extensively experiments on different datasets compared with state-of-the-art approaches.

Key facts. Cited by 95 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Jul 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 31; 2022: 29; 2023: 20; 2024: 6; 2025: 6; 2026: 3.

95 papers.

Sort:

By area:

  1. 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 276
  2. 2023Cross-Entropy Loss Functions: Theoretical Analysis and Applicationscited by 206
  3. 2024CycleResearcher: Improving Automated Research via Automated Reviewcited by 142
  4. 2022Frequency-driven Imperceptible Adversarial Attack on Semantic Similaritycited by 76
  5. 2022SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustnesscited by 74
  6. 2023How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defensescited by 65
  7. 2022Practical Evaluation of Adversarial Robustness via Adaptive Auto Attackcited by 44
  8. 2022A Survey of Robust Adversarial Training in Pattern Recognition: Fundamental, Theory, and Methodologiescited by 44
  9. 2022Enhancing Adversarial Training with Second-Order Statistics of Weightscited by 42
  10. 2021Few-shot Backdoor Defense Using Shapley Estimationcited by 40
  11. 2022A Unified Wasserstein Distributional Robustness Framework for Adversarial Trainingcited by 36
  12. 2022DISCO: Adversarial Defense with Local Implicit Functionscited by 33
38 more
  1. 2022An Overview of Compressible and Learnable Image Transformation with Secret Key and Its Applicationscited by 29
  2. 2021AdvRush: Searching for Adversarially Robust Neural Architecturescited by 28
  3. 2023Randomized Adversarial Training via Taylor Expansioncited by 28
  4. 2021Combating Adversaries with Anti-Adversariescited by 27
  5. 2022TokenMixup: Efficient Attention-guided Token-level Data Augmentation for Transformerscited by 26
  6. 2024FuRL: Visual-Language Models as Fuzzy Rewards for Reinforcement Learningcited by 26
  7. 2021LAFEAT: Piercing Through Adversarial Defenses with Latent Featurescited by 24
  8. 2023Improving Generalization of Adversarial Training via Robust Critical Fine-Tuningcited by 23
  9. 2021Automated Discovery of Adaptive Attacks on Adversarial Defensescited by 22
  10. 2021Robustness of on-device Models: Adversarial Attack to Deep Learning Models on Android Appscited by 19
  11. 2021Predify: Augmenting deep neural networks with brain-inspired predictive coding dynamicscited by 19
  12. 2023Improving the Accuracy-Robustness Trade-Off of Classifiers via Adaptive Smoothingcited by 18
  13. 2021Adversarial Examples can be Effective Data Augmentation for Unsupervised Machine Learningcited by 16
  14. 2021Adversarial Reinforced Instruction Attacker for Robust Vision-Language Navigationcited by 15
  15. 2022My Face My Choice: Privacy Enhancing Deepfakes for Social Media Anonymizationcited by 14
  16. 2023Efficient Adversarial Contrastive Learning via Robustness-Aware Coreset Selectioncited by 14
  17. 2022Improving Robustness by Enhancing Weak Subnetscited by 12
  18. 2022Increasing Confidence in Adversarial Robustness Evaluationscited by 12
  19. 2021Finding Optimal Tangent Points for Reducing Distortions of Hard-label Attackscited by 11
  20. 2022Global-Local Regularization Via Distributional Robustnesscited by 11
  21. 2022How Does Frequency Bias Affect the Robustness of Neural Image Classifiers against Common Corruption and Adversarial Perturbations?cited by 11
  22. 2021AGKD-BML: Defense Against Adversarial Attack by Attention Guided Knowledge Distillation and Bi-directional Metric Learningcited by 10
  23. 2021Improving Model Robustness with Latent Distribution Locally and Globallycited by 9
  24. 2021Understanding and Achieving Efficient Robustness with Adversarial Supervised Contrastive Learningcited by 8
  25. 2023Defense against Adversarial Cloud Attack on Remote Sensing Salient Object Detectioncited by 8
  26. 2021Perceptually Constrained Adversarial Attackscited by 7
  27. 2021Domain Invariant Adversarial Learningcited by 7
  28. 2022InfoAT: Improving Adversarial Training Using the Information Bottleneck Principlecited by 7
  29. 2022Reliable Robustness Evaluation via Automatically Constructed Attack Ensemblescited by 6
  30. 2023Provable Unrestricted Adversarial Training without Compromise with Generalizabilitycited by 6
  31. 2023Adversarial Finetuning with Latent Representation Constraint to Mitigate Accuracy-Robustness Tradeoffcited by 6
  32. 2024Adversarial Training: A Surveycited by 6
  33. 2021Adversarial Robustness of Deep Learning: Theory, Algorithms, and Applicationscited by 5
  34. 2022Towards an Awareness of Time Series Anomaly Detection Models' Adversarial Vulnerabilitycited by 5
  35. 2023Adversarial Attacks and Defenses in Machine Learning-Powered Networks: A Contemporary Surveycited by 5
  36. 2023Robustness-enhanced Uplift Modeling with Adversarial Feature Desensitizationcited by 5
  37. 2021Explaining Adversarial Vulnerability with a Data Sparsity Hypothesiscited by 4
  38. 2021Quality Assurance Challenges for Machine Learning Software Applications During Software Development Life Cycle Phasescited by 4

50 most cited of 95 All 95 (JSON)