mlsanityData to 7 Oct 2026

A Unified Approach to Interpreting and Boosting Adversarial Transferability

arXiv 2010.04055 ↗First posted 8 Oct 2020cs.LG cs.AI cs.CVcited by 71

Not on the map. Why?

Abstract (arXiv)

In this paper, we use the interaction inside adversarial perturbations to explain and boost the adversarial transferability. We discover and prove the negative correlation between the adversarial transferability and the interaction inside adversarial perturbations. The negative correlation is further verified through different DNNs with various inputs. Moreover, this negative correlation can be regarded as a unified perspective to understand current transferability-boosting methods. To this end, we prove that some classic methods of enhancing the transferability essentially decease interactions inside adversarial perturbations. Based on this, we propose to directly penalize interactions during the attacking process, which significantly improves the adversarial transferability.

Key facts. Cited by 71 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 22; 2022: 9; 2023: 15; 2024: 15; 2025: 6; 2026: 4.

71 papers.

Sort:

By area:

  1. 2021Unlearnable Examples: Making Personal Data Unexploitablecited by 188
  2. 2021Towards Transferable Adversarial Attacks on Vision Transformerscited by 80
  3. 2021Improving Adversarial Robustness via Channel-wise Activation Suppressingcited by 76
  4. 2021Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networkscited by 73
  5. 2024Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Surveycited by 52
  6. 2023A Survey on Transferability of Adversarial Examples across Deep Neural Networkscited by 43
  7. 2021Discovering and Explaining the Representation Bottleneck of DNNscited by 42
  8. 2021TRS: Transferability Reduced Ensemble via Encouraging Gradient Diversity and Model Smoothnesscited by 37
  9. 2021Defining and Quantifying the Emergence of Sparse Concepts in DNNscited by 36
  10. 2022Towards Understanding and Boosting Adversarial Transferability from a Distribution Perspectivecited by 36
  11. 2021Analysis and Applications of Class-wise Robustness in Adversarial Trainingcited by 33
  12. 2023Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferabilitycited by 32
38 more
  1. 2023Generalizable Black-Box Adversarial Attack with Meta Learningcited by 29
  2. 2023Does a Neural Network Really Encode Symbolic Concepts?cited by 27
  3. 2022Investigating Top-k White-Box and Transferable Black-box Attackcited by 26
  4. 2023Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspectivecited by 19
  5. 2024Semantic-Aligned Adversarial Evolution Triangle for High-Transferability Vision-Language Attackcited by 18
  6. 2021A Unified Game-Theoretic Interpretation of Adversarial Robustnesscited by 17
  7. 2023Adversarial Examples Are Not Real Featurescited by 16
  8. 2021Training Meta-Surrogate Model for Transferable Adversarial Attackcited by 15
  9. 2021Adversarial Examples on Segmentation Models Can be Easy to Transfercited by 15
  10. 2022Projective Ranking-based GNN Evasion Attackscited by 14
  11. 2021Interpreting Attributions and Interactions of Adversarial Attackscited by 13
  12. 2022Towards Transferable Unrestricted Adversarial Examples with Minimum Changescited by 13
  13. 2024Exploring the Robustness of In-Context Learning with Noisy Labelscited by 13
  14. 2024Towards the Dynamics of a DNN Learning Symbolic Interactionscited by 13
  15. 2023Reliable Evaluation of Adversarial Transferabilitycited by 12
  16. 2021Finding Optimal Tangent Points for Reducing Distortions of Hard-label Attackscited by 11
  17. 2023Can the Inference Logic of Large Language Models be Disentangled into Symbolic Concepts?cited by 11
  18. 2021Can We Faithfully Represent Masked States to Compute Shapley Values on a DNN?cited by 10
  19. 2023Technical Note: Defining and Quantifying AND-OR Interactions for Faithful and Concise Explanation of DNNscited by 10
  20. 2025INTER: Mitigating Hallucination in Large Vision-Language Models by Interaction Guidance Samplingcited by 10
  21. 2022An Intermediate-level Attack Framework on The Basis of Linear Regressioncited by 9
  22. 2023Bayesian Neural Networks Avoid Encoding Complex and Perturbation-Sensitive Conceptscited by 9
  23. 2021What Do Deep Nets Learn? Class-wise Patterns Revealed in the Input Spacecited by 8
  24. 2023Where We Have Arrived in Proving the Emergence of Sparse Symbolic Concepts in AI Modelscited by 8
  25. 2021Visualizing the Emergence of Intermediate Visual Patterns in DNNscited by 7
  26. 2024Diagnosing the Compositional Knowledge of Vision Language Models from a Game-Theoretic Viewcited by 7
  27. 2021Adaptive Perturbation for Adversarial Attackcited by 6
  28. 2023SoK: Pitfalls in Evaluating Black-Box Attackscited by 6
  29. 2023Towards Evaluating Transfer-based Attacks Systematically, Practically, and Fairlycited by 6
  30. 2024Adversarial Example Soups: Improving Transferability and Stealthiness for Freecited by 6
  31. 2024PeerAiD: Improving Adversarial Distillation from a Specialized Peer Tutorcited by 6
  32. 2024Identifying Important Group of Pixels using Interactionscited by 5
  33. 2024SongBsAb: A Dual Prevention Approach against Singing Voice Conversion based Illegal Song Coverscited by 5
  34. 2024Two-Phase Dynamics of Interactions Explains the Starting Point of a DNN Learning Over-Fitted Featurescited by 5
  35. 2021Exploring Transferable and Robust Adversarial Perturbation Generation from the Perspective of Network Hierarchycited by 4
  36. 2021Moir'e Attack (MA): A New Potential Risk of Screen Photoscited by 4
  37. 2022Enhance transferability of adversarial examples with model architecturecited by 4
  38. 2024ReToMe-VA: Recursive Token Merging for Video Diffusion-based Unrestricted Adversarial Attackcited by 3

50 most cited of 71 All 71 (JSON)