# A Unified Approach to Interpreting and Boosting Adversarial Transferability

arXiv: https://arxiv.org/abs/2010.04055 · HTML: https://mlsanity.com/paper/2010.04055/

## Key facts

- Cited by 71 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Oct 2020.

## Built on by (most cited first, 30 of 71)

- [Unlearnable Examples: Making Personal Data Unexploitable](https://mlsanity.com/paper/2101.04898/) (2021)
- [Towards Transferable Adversarial Attacks on Vision Transformers](https://mlsanity.com/paper/2109.04176/) (2021)
- [Improving Adversarial Robustness via Channel-wise Activation Suppressing](https://mlsanity.com/paper/2103.08307/) (2021)
- [Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks](https://mlsanity.com/paper/2110.03825/) (2021)
- [Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2412.02104/) (2024)
- [A Survey on Transferability of Adversarial Examples across Deep Neural Networks](https://mlsanity.com/paper/2310.17626/) (2023)
- [Discovering and Explaining the Representation Bottleneck of DNNs](https://mlsanity.com/paper/2111.06236/) (2021)
- [TRS: Transferability Reduced Ensemble via Encouraging Gradient Diversity and Model Smoothness](https://mlsanity.com/paper/2104.00671/) (2021)
- [Towards Understanding and Boosting Adversarial Transferability from a Distribution Perspective](https://mlsanity.com/paper/2210.04213/) (2022)
- [Defining and Quantifying the Emergence of Sparse Concepts in DNNs](https://mlsanity.com/paper/2111.06206/) (2021)
- [Analysis and Applications of Class-wise Robustness in Adversarial Training](https://mlsanity.com/paper/2105.14240/) (2021)
- [Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability](https://mlsanity.com/paper/2307.07873/) (2023)
- [Generalizable Black-Box Adversarial Attack with Meta Learning](https://mlsanity.com/paper/2301.00364/) (2023)
- [Does a Neural Network Really Encode Symbolic Concepts?](https://mlsanity.com/paper/2302.13080/) (2023)
- [Investigating Top-k White-Box and Transferable Black-box Attack](https://mlsanity.com/paper/2204.00089/) (2022)
- [Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspective](https://mlsanity.com/paper/2302.09457/) (2023)
- [Semantic-Aligned Adversarial Evolution Triangle for High-Transferability Vision-Language Attack](https://mlsanity.com/paper/2411.02669/) (2024)
- [A Unified Game-Theoretic Interpretation of Adversarial Robustness](https://mlsanity.com/paper/2111.03536/) (2021)
- [Adversarial Examples Are Not Real Features](https://mlsanity.com/paper/2310.18936/) (2023)
- [Training Meta-Surrogate Model for Transferable Adversarial Attack](https://mlsanity.com/paper/2109.01983/) (2021)
- [Adversarial Examples on Segmentation Models Can be Easy to Transfer](https://mlsanity.com/paper/2111.11368/) (2021)
- [Projective Ranking-based GNN Evasion Attacks](https://mlsanity.com/paper/2202.12993/) (2022)
- [Exploring the Robustness of In-Context Learning with Noisy Labels](https://mlsanity.com/paper/2404.18191/) (2024)
- [Interpreting Attributions and Interactions of Adversarial Attacks](https://mlsanity.com/paper/2108.06895/) (2021)
- [Towards Transferable Unrestricted Adversarial Examples with Minimum Changes](https://mlsanity.com/paper/2201.01102/) (2022)
- [Reliable Evaluation of Adversarial Transferability](https://mlsanity.com/paper/2306.08565/) (2023)
- [Towards the Dynamics of a DNN Learning Symbolic Interactions](https://mlsanity.com/paper/2407.19198/) (2024)
- [Technical Note: Defining and Quantifying AND-OR Interactions for Faithful and Concise Explanation of DNNs](https://mlsanity.com/paper/2304.13312/) (2023)
- [Finding Optimal Tangent Points for Reducing Distortions of Hard-label Attacks](https://mlsanity.com/paper/2111.07492/) (2021)
- [Can the Inference Logic of Large Language Models be Disentangled into Symbolic Concepts?](https://mlsanity.com/paper/2304.01083/) (2023)

## 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.