mlsanityData to 7 Oct 2026

Defending against Whitebox Adversarial Attacks via Randomized Discretization

arXiv 1903.10586 ↗First posted 25 Mar 2019cs.LG cs.CR stat.MLcited by 29

Not on the map. Why?

Abstract (arXiv)

Adversarial perturbations dramatically decrease the accuracy of state-of-the-art image classifiers. In this paper, we propose and analyze a simple and computationally efficient defense strategy: inject random Gaussian noise, discretize each pixel, and then feed the result into any pre-trained classifier. Theoretically, we show that our randomized discretization strategy reduces the KL divergence between original and adversarial inputs, leading to a lower bound on the classification accuracy of any classifier against any (potentially whitebox) ℓ_∞-bounded adversarial attack. Empirically, we evaluate our defense on adversarial examples generated by a strong iterative PGD attack. On ImageNet, our defense is more robust than adversarially-trained networks and the winning defenses of the NIPS 2017 Adversarial Attacks & Defenses competition.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 5; 2023: 9; 2024: 5; 2025: 1; 2026: 1.

29 papers.

Sort:

By area:

  1. 2024Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Roboticscited by 68
  2. 2022Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patchescited by 57
  3. 2023TPatch: A Triggered Physical Adversarial Patchcited by 22
  4. 2021Universal Spectral Adversarial Attacks for Deformable Shapescited by 14
  5. 2022Demystifying the Adversarial Robustness of Random Transformation Defensescited by 14
  6. 2021Learning Diverse-Structured Networks for Adversarial Robustnesscited by 12
  7. 2023AdvART: Adversarial Art for Camouflaged Object Detection Attackscited by 12
  8. 2023SAAM: Stealthy Adversarial Attack on Monocular Depth Estimationcited by 12
  9. 2023APARATE: Adaptive Adversarial Patch for CNN-based Monocular Depth Estimation for Autonomous Navigationcited by 10
  10. 2023Outlier Robust Adversarial Trainingcited by 10
  11. 2023Reliable learning in challenging environmentscited by 9
  12. 2021The art of defense: letting networks fool the attackercited by 6
17 more
  1. 2021Selection of Source Images Heavily Influences the Effectiveness of Adversarial Attackscited by 6
  2. 2021Improving the Robustness of Adversarial Attacks Using an Affine-Invariant Gradient Estimatorcited by 6
  3. 2022Rethinking Textual Adversarial Defense for Pre-trained Language Modelscited by 5
  4. 2024ControlLoc: Physical-World Hijacking Attack on Visual Perception in Autonomous Drivingcited by 5
  5. 2023Improving Adversarial Transferability with Scheduled Step Size and Dual Examplecited by 3
  6. 2024SlowPerception: Physical-World Latency Attack against Visual Perception in Autonomous Drivingcited by 3
  7. 2023Runtime Stealthy Perception Attacks against DNN-based Adaptive Cruise Control Systemscited by 1
  8. 2024A Novel Perturb-ability Score to Mitigate Evasion Adversarial Attacks on Flow-Based ML-NIDScited by 1
  9. 2021Constant Random Perturbations Provide Adversarial Robustness with Minimal Effect on Accuracycited by 0
  10. 2021MixDefense: A Defense-in-Depth Framework for Adversarial Example Detection Based on Statistical and Semantic Analysiscited by 0
  11. 2021On Procedural Adversarial Noise Attack And Defensecited by 0
  12. 2022Pixel to Binary Embedding Towards Robustness for CNNscited by 0
  13. 2022Scoring Black-Box Models for Adversarial Robustnesscited by 0
  14. 2023Adversarial Defenses via Vector Quantizationcited by 0
  15. 2024Physical Adversarial Attack on Monocular Depth Estimation via Shape-Varying Patchescited by 0
  16. 2025T2I-Based Physical-World Appearance Attack against Traffic Sign Recognition Systems in Autonomous Drivingcited by 0
  17. 2026A Classifier-Agnostic Zero-Shot Adversarial Attack Detection via CLIPcited by 0