mlsanityData to 14 Oct 2026

Improving Model Robustness with Latent Distribution Locally and Globally

arXiv 2107.04401 ↗First posted 8 Jul 2021cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

In this work, we consider model robustness of deep neural networks against adversarial attacks from a global manifold perspective. Leveraging both the local and global latent information, we propose a novel adversarial training method through robust optimization, and a tractable way to generate Latent Manifold Adversarial Examples (LMAEs) via an adversarial game between a discriminator and a classifier. The proposed adversarial training with latent distribution (ATLD) method defends against adversarial attacks by crafting LMAEs with the latent manifold in an unsupervised manner. ATLD preserves the local and global information of latent manifold and promises improved robustness against adversarial attacks. To verify the effectiveness of our proposed method, we conduct extensive experiments over different datasets (e.g., CIFAR-10, CIFAR-100, SVHN) with different adversarial attacks (e.g., PGD, CW), and show that our method substantially outperforms the state-of-the-art (e.g., Feature Scattering) in adversarial robustness by a large accuracy margin. The source codes are available at https://github.com/LitterQ/ATLD-pytorch.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 41 of its 55 references that are in the map. First posted on arXiv 8 Jul 2021.

Builds on

41 of 55 references.

References · 41

  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. 2016Wide Residual Networkscited by 3,070
  5. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  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. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 953
  10. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 920
  11. 2017Wasserstein GANcited by 639
  12. 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 565
29 more
  1. 2016f-GAN: Training Generative Neural Samplers using Variational Divergence Minimizationcited by 506
  2. 2020Overfitting in adversarially robust deep learningcited by 506
  3. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 464
  4. 2019Unlabeled Data Improves Adversarial Robustnesscited by 416
  5. 2019Using Pre-Training Can Improve Model Robustness and Uncertaintycited by 373
  6. 2018Adversarially Robust Generalization Requires More Datacited by 318
  7. 2020Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examplescited by 278
  8. 2018Audio Adversarial Examples: Targeted Attacks on Speech-to-Textcited by 274
  9. 2017MagNet: a Two-Pronged Defense against Adversarial Examplescited by 269
  10. 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 244
  11. 2017On Detecting Adversarial Perturbationscited by 232
  12. 2018Adversarial Logit Pairingcited by 224
  13. 2017On the (Statistical) Detection of Adversarial Examplescited by 180
  14. 2016Mode Regularized Generative Adversarial Networkscited by 123
  15. 2020RayS: A Ray Searching Method for Hard-label Adversarial Attackcited by 96
  16. 2019Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Trainingcited by 95
  17. 2018Improving DNN Robustness to Adversarial Attacks using Jacobian Regularizationcited by 88
  18. 2019Metric Learning for Adversarial Robustnesscited by 77
  19. 2019Adversarially Robust Generalization Just Requires More Unlabeled Datacited by 76
  20. 2019Training Robust Deep Neural Networks via Adversarial Noise Propagationcited by 62
  21. 2017Adversarial and Clean Data Are Not Twinscited by 52
  22. 2018Bilateral Adversarial Training: Towards Fast Training of More Robust Models Against Adversarial Attackscited by 48
  23. 2015A Unified Gradient Regularization Family for Adversarial Examplescited by 43
  24. 2019Jacobian Adversarially Regularized Networks for Robustnesscited by 40
  25. 2018Greedy Attack and Gumbel Attack: Generating Adversarial Examples for Discrete Datacited by 38
  26. 2017Adversarial Examples for Semantic Image Segmentationcited by 33
  27. 2019Harnessing the Vulnerability of Latent Layers in Adversarially Trained Modelscited by 26
  28. 2018Adversarial Noise Layer: Regularize Neural Network By Adding Noisecited by 25
  29. 2019Image Synthesis with a Single (Robust) Classifiercited by 9

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 2; 2023: 3; 2024: 0; 2025: 2.

9 papers.

  1. 2023Cross-Entropy Loss Functions: Theoretical Analysis and Applicationscited by 210
  2. 2022Evaluating the Adversarial Robustness of Adaptive Test-time Defensescited by 64
  3. 2022A Survey of Robust Adversarial Training in Pattern Recognition: Fundamental, Theory, and Methodologiescited by 44
  4. 2025AutoAdvExBench: Benchmarking autonomous exploitation of adversarial example defensescited by 15
  5. 2021Push Stricter to Decide Better: A Class-Conditional Feature Adaptive Framework for Improving Adversarial Robustnesscited by 6
  6. 2021Adversarial Robustness of Deep Learning: Theory, Algorithms, and Applicationscited by 5
  7. 2025Beyond Vulnerabilities: A Survey of Adversarial Attacks as Both Threats and Defenses in Computer Vision Systemscited by 4
  8. 2023Robust Feature Inference: A Test-time Defense Strategy using Spectral Projectionscited by 3
  9. 2023Topology-preserving Adversarial Training for Alleviating Natural Accuracy Degradationcited by 1