mlsanityData to 7 Oct 2026

Improving Transferability of Adversarial Examples via Bayesian Attacks

arXiv 2307.11334 ↗First posted 21 Jul 2023cs.LG cs.CR cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

The transferability of adversarial examples allows for the attack on unknown deep neural networks (DNNs), posing a serious threat to many applications and attracting great attention. In this paper, we improve the transferability of adversarial examples by incorporating the Bayesian formulation into both the model parameters and model input, enabling their joint diversification. We demonstrate that combination of Bayesian formulations for both the model input and model parameters yields significant improvements in transferability. By introducing advanced approximations of the posterior distribution over the model input, adversarial transferability achieves further enhancement, surpassing all state-of-the-arts when attacking without model fine-tuning. Additionally, we propose a principled approach to fine-tune model parameters within this Bayesian framework. Extensive experiments demonstrate that our method achieves a new state-of-the-art in transfer-based attacks, significantly improving the average success rate on ImageNet and CIFAR-10. Code at: https://github.com/qizhangli/MoreBayesian-jrnl.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 82 of its 111 references that are in the map. First posted on arXiv 21 Jul 2023.

Builds on

82 of 111 references.

References · 82

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  6. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  7. 2016Densely Connected Convolutional Networkscited by 6,691
  8. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  9. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  10. 2013Intriguing properties of neural networkscited by 5,114
  11. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  12. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
38 more
  1. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  2. 2022A ConvNet for the 2020scited by 3,545
  3. 2016Wide Residual Networkscited by 3,057
  4. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  5. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,360
  6. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  7. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  8. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  9. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
  10. 2020Sharpness-Aware Minimization for Efficiently Improving Generalizationcited by 1,404
  11. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  12. 2018Averaging Weights Leads to Wider Optima and Better Generalizationcited by 1,194
  13. 2016Adversarial Machine Learning at Scalecited by 934
  14. 2020Fast is better than free: Revisiting adversarial trainingcited by 723
  15. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 659
  16. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 591
  17. 2019A Simple Baseline for Bayesian Uncertainty in Deep Learningcited by 555
  18. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 530
  19. 2017Countering Adversarial Images using Input Transformationscited by 517
  20. 2017Adversarial Patchcited by 514
  21. 2015Variational Dropout and the Local Reparameterization Trickcited by 489
  22. 2020Bayesian Deep Learning and a Probabilistic Perspective of Generalizationcited by 480
  23. 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 440
  24. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 439
  25. 2017Mitigating Adversarial Effects Through Randomizationcited by 382
  26. 2019Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attackscited by 352
  27. 2017Stochastic Gradient Descent as Approximate Bayesian Inferencecited by 298
  28. 2019Adversarial Examples Improve Image Recognitioncited by 283
  29. 2019Searching for A Robust Neural Architecture in Four GPU Hourscited by 258
  30. 2017Concrete Dropoutcited by 227
  31. 2021Are Transformers More Robust Than CNNs?cited by 187
  32. 2020A Self-supervised Approach for Adversarial Robustnesscited by 180
  33. 2019Efficient Decision-based Black-box Adversarial Attacks on Face Recognitioncited by 173
  34. 2020Efficient and Scalable Bayesian Neural Nets with Rank-1 Factorscited by 171
  35. 2016Deep Pyramidal Residual Networkscited by 163
  36. 2019AdvHat: Real-world adversarial attack on ArcFace Face ID systemcited by 161
  37. 2019Practical Deep Learning with Bayesian Principlescited by 158
  38. 2021Admix: Enhancing the Transferability of Adversarial Attackscited by 155

50 most cited of 82 All 82 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 0; 2026: 1.

3 papers.

  1. 2024Improved Generation of Adversarial Examples Against Safety-aligned LLMscited by 17
  2. 2024SoK: Analyzing Adversarial Examples: A Framework to Study Adversary Knowledgecited by 1
  3. 2026Content Fuzzing for Escaping Information Cocoons on Digital Social Mediacited by 1