mlsanityData to 14 Oct 2026

Preemptive Image Robustification for Protecting Users against Man-in-the-Middle Adversarial Attacks

arXiv 2112.05634 ↗First posted 10 Dec 2021cs.LG cs.CR cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Deep neural networks have become the driving force of modern image recognition systems. However, the vulnerability of neural networks against adversarial attacks poses a serious threat to the people affected by these systems. In this paper, we focus on a real-world threat model where a Man-in-the-Middle adversary maliciously intercepts and perturbs images web users upload online. This type of attack can raise severe ethical concerns on top of simple performance degradation. To prevent this attack, we devise a novel bi-level optimization algorithm that finds points in the vicinity of natural images that are robust to adversarial perturbations. Experiments on CIFAR-10 and ImageNet show our method can effectively robustify natural images within the given modification budget. We also show the proposed method can improve robustness when jointly used with randomized smoothing.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 28 of its 34 references that are in the map. First posted on arXiv 10 Dec 2021.

Builds on

28 of 34 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  6. 2013Intriguing properties of neural networkscited by 5,155
  7. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  8. 2016Wide Residual Networkscited by 3,070
  9. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
  10. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  11. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
  12. 2018Robustness May Be at Odds with Accuracycited by 880
16 more
  1. 2020Fast is better than free: Revisiting adversarial trainingcited by 727
  2. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 567
  3. 2020Overfitting in adversarially robust deep learningcited by 506
  4. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 468
  5. 2019Provably Robust Deep Learning via Adversarially Trained Smoothed Classifierscited by 330
  6. 2018Certified Defenses against Adversarial Examplescited by 306
  7. 2020Attacks Which Do Not Kill Training Make Adversarial Learning Strongercited by 243
  8. 2019You Only Propagate Once: Accelerating Adversarial Training via Maximal Principlecited by 183
  9. 2020Randomized Smoothing of All Shapes and Sizescited by 147
  10. 2019Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Trainingcited by 95
  11. 2021LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognitioncited by 94
  12. 2020Unadversarial Examples: Designing Objects for Robust Visioncited by 45
  13. 2017Adversarial Image Perturbation for Privacy Protection -- A Game Theory Perspectivecited by 38
  14. 2018Adversarial Perturbations Against Real-Time Video Classification Systemscited by 32
  15. 2019Man-in-the-Middle Attacks against Machine Learning Classifiers via Malicious Generative Modelscited by 19
  16. 2019Image Synthesis with a Single (Robust) Classifiercited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 0; 2025: 0; 2026: 2.

4 papers.

  1. 2023The Best Defense is a Good Offense: Adversarial Augmentation against Adversarial Attackscited by 15
  2. 2023Adversarial Examples in the Physical World: A Surveycited by 10
  3. 2026Do Agents Dream of False Memories? Black-box Visual Attacks on Long-term Memory in Multimodal AI Agentscited by 2
  4. 2026Fast Preemptive Robustification: High-Frequency Response Anti-Aligns Shared Vulnerabilitycited by 0