mlsanityData to 7 Oct 2026

ME-Net: Towards Effective Adversarial Robustness with Matrix Estimation

arXiv 1905.11971 ↗First posted 28 May 2019cs.LG cs.CV stat.MLcited by 65

Not on the map. Why?

Abstract (arXiv)

Deep neural networks are vulnerable to adversarial attacks. The literature is rich with algorithms that can easily craft successful adversarial examples. In contrast, the performance of defense techniques still lags behind. This paper proposes ME-Net, a defense method that leverages matrix estimation (ME). In ME-Net, images are preprocessed using two steps: first pixels are randomly dropped from the image; then, the image is reconstructed using ME. We show that this process destroys the adversarial structure of the noise, while re-enforcing the global structure in the original image. Since humans typically rely on such global structures in classifying images, the process makes the network mode compatible with human perception. We conduct comprehensive experiments on prevailing benchmarks such as MNIST, CIFAR-10, SVHN, and Tiny-ImageNet. Comparing ME-Net with state-of-the-art defense mechanisms shows that ME-Net consistently outperforms prior techniques, improving robustness against both black-box and white-box attacks.

Key facts. Cited by 65 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 21; 2022: 15; 2023: 12; 2024: 10; 2025: 6; 2026: 1.

65 papers.

Sort:

By area:

  1. 2022Diffusion Models for Adversarial Purificationcited by 469
  2. 2021Improving Robustness using Generated Datacited by 233
  3. 2021Adversarial purification with Score-based generative modelscited by 132
  4. 2021Targeted Supervised Contrastive Learning for Long-Tailed Recognitioncited by 132
  5. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  6. 2022Guided Diffusion Model for Adversarial Purificationcited by 90
  7. 2021Towards Robustness Against Natural Language Word Substitutionscited by 68
  8. 2023Robust Evaluation of Diffusion-Based Adversarial Purificationcited by 65
  9. 2022Evaluating the Adversarial Robustness of Adaptive Test-time Defensescited by 64
  10. 2022AdvDO: Realistic Adversarial Attacks for Trajectory Predictioncited by 48
  11. 2022A Survey of Robust Adversarial Training in Pattern Recognition: Fundamental, Theory, and Methodologiescited by 44
  12. 2021CausalAdv: Adversarial Robustness through the Lens of Causalitycited by 37
38 more
  1. 2022Indiscriminate Poisoning Attacks on Unsupervised Contrastive Learningcited by 32
  2. 2023Subclass-balancing Contrastive Learning for Long-tailed Recognitioncited by 26
  3. 2022Threat Model-Agnostic Adversarial Defense using Diffusion Modelscited by 24
  4. 2022On the Limitations of Stochastic Pre-processing Defensescited by 21
  5. 2023Enhancing Adversarial Robustness via Score-Based Optimizationcited by 19
  6. 2023MimicDiffusion: Purifying Adversarial Perturbation via Mimicking Clean Diffusion Modelcited by 18
  7. 2021MagDR: Mask-guided Detection and Reconstruction for Defending Deepfakescited by 17
  8. 2023Convolutional Visual Prompt for Robust Visual Perceptioncited by 17
  9. 2022Robust Trajectory Prediction against Adversarial Attackscited by 16
  10. 2022PointDP: Diffusion-driven Purification against Adversarial Attacks on 3D Point Cloud Recognitioncited by 16
  11. 2024Adversarial Training on Purification (AToP): Advancing Both Robustness and Generalizationcited by 15
  12. 2023Purify++: Improving Diffusion-Purification with Advanced Diffusion Models and Control of Randomnesscited by 13
  13. 2022CausalSim: A Causal Framework for Unbiased Trace-Driven Simulationcited by 10
  14. 2024Adversarial Guided Diffusion Models for Adversarial Purificationcited by 8
  15. 2025Diffusion-based Adversarial Purification from the Perspective of the Frequency Domaincited by 7
  16. 2021The art of defense: letting networks fool the attackercited by 6
  17. 2024Robust Overfitting Does Matter: Test-Time Adversarial Purification With FGSMcited by 6
  18. 2024DiffBreak: Is Diffusion-Based Purification Robust?cited by 6
  19. 2022Adversarial Vulnerability of Randomized Ensemblescited by 5
  20. 2024Classifier Guidance Enhances Diffusion-based Adversarial Purification by Preserving Predictive Informationcited by 5
  21. 2021Explaining Adversarial Vulnerability with a Data Sparsity Hypothesiscited by 4
  22. 2021Regional Adversarial Training for Better Robust Generalizationcited by 4
  23. 2022Exploring Adversarial Attacks and Defenses in Vision Transformers trained with DINOcited by 4
  24. 2023Combining Explicit and Implicit Regularization for Efficient Learning in Deep Networkscited by 4
  25. 2021The Effect of Prior Lipschitz Continuity on the Adversarial Robustness of Bayesian Neural Networkscited by 3
  26. 2021Detect and Defense Against Adversarial Examples in Deep Learning using Natural Scene Statistics and Adaptive Denoisingcited by 3
  27. 2021SEC4SR: A Security Analysis Platform for Speaker Recognitioncited by 3
  28. 2022Hindering Adversarial Attacks with Implicit Neural Representationscited by 3
  29. 2023On the Robustness of Randomized Ensembles to Adversarial Perturbationscited by 3
  30. 2025One Stone, Two Birds: Enhancing Adversarial Defense Through the Lens of Distributional Discrepancycited by 3
  31. 2021Adversarial Machine Learning in Text Analysis and Generationcited by 2
  32. 2024Learning from Reduced Labels for Long-Tailed Datacited by 2
  33. 2024Cutting through buggy adversarial example defenses: fixing 1 line of code breaks Sabrecited by 2
  34. 2021Defensive Tensorizationcited by 1
  35. 2021Denoised Internal Models: a Brain-Inspired Autoencoder against Adversarial Attackscited by 1
  36. 2023Matrix Estimation for Individual Fairnesscited by 1
  37. 2023Language Guided Adversarial Purificationcited by 1
  38. 2024Tropical Decision Boundaries for Neural Networks Are Robust Against Adversarial Attackscited by 1

50 most cited of 65 All 65 (JSON)