How to choose your best allies for a transferable attack?
Not on the map. Why?
Abstract (arXiv)
The transferability of adversarial examples is a key issue in the security of deep neural networks. The possibility of an adversarial example crafted for a source model fooling another targeted model makes the threat of adversarial attacks more realistic. Measuring transferability is a crucial problem, but the Attack Success Rate alone does not provide a sound evaluation. This paper proposes a new methodology for evaluating transferability by putting distortion in a central position. This new tool shows that transferable attacks may perform far worse than a black box attack if the attacker randomly picks the source model. To address this issue, we propose a new selection mechanism, called FiT, which aims at choosing the best source model with only a few preliminary queries to the target. Our experimental results show that FiT is highly effective at selecting the best source model for multiple scenarios such as single-model attacks, ensemble-model attacks and multiple attacks (Code available at: https://github.com/t-maho/transferability_measure_fit).
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 35 of its 41 references that are in the map. First posted on arXiv 5 Apr 2023.
Builds on
35 of 41 references.
References · 35
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
- 2016Adversarial examples in the physical worldcited by 1,762
- 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
- 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 591
- 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 530
- 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 440
- 2019Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attackscited by 352
- 2017The Space of Transferable Adversarial Examplescited by 156
- 2021Admix: Enhancing the Transferability of Adversarial Attackscited by 155
- 2019Enhancing Adversarial Example Transferability with an Intermediate Level Attackcited by 139
- 2021Feature Importance-aware Transferable Adversarial Attackscited by 125
23 more
- 2020QEBA: Query-Efficient Boundary-Based Blackbox Attackcited by 103
- 2020RayS: A Ray Searching Method for Hard-label Adversarial Attackcited by 94
- 2022Improving Adversarial Transferability via Neuron Attribution-Based Attackscited by 92
- 2019Deep Neural Network Fingerprinting by Conferrable Adversarial Examplescited by 90
- 2021Stochastic Variance Reduced Ensemble Adversarial Attack for Boosting the Adversarial Transferabilitycited by 84
- 2021On Improving Adversarial Transferability of Vision Transformerscited by 70
- 2018Learning Transferable Adversarial Examples via Ghost Networkscited by 69
- 2019IPGuard: Protecting Intellectual Property of Deep Neural Networks via Fingerprinting the Classification Boundarycited by 68
- 2020GeoDA: a geometric framework for black-box adversarial attackscited by 66
- 2020SurFree: a fast surrogate-free black-box attackcited by 59
- 2022Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbationscited by 58
- 2021Boosting Adversarial Transferability through Enhanced Momentumcited by 53
- 2021Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraintscited by 50
- 2021Improving the Transferability of Adversarial Examples with Resized-Diverse-Inputs, Diversity-Ensemble and Region Fittingcited by 37
- 2022Transferable Adversarial Attack based on Integrated Gradientscited by 35
- 2019Walking on the Edge: Fast, Low-Distortion Adversarial Examplescited by 18
- 2020On the Transferability of Adversarial Attacksagainst Neural Text Classifiercited by 16
- 2022Towards Good Practices in Evaluating Transfer Adversarial Attackscited by 14
- 2018On the Transferability of Adversarial Examples Against CNN-Based Image Forensicscited by 12
- 2019Measuring the Transferability of Adversarial Examplescited by 6
- 2021Direction-Aggregated Attack for Transferable Adversarial Examplescited by 6
- 2022Enhancing Targeted Attack Transferability via Diversified Weight Pruningcited by 2
- 2022FBI: Fingerprinting models with Benign Inputscited by 1
Built on by
Citing papers per year: 2023: 1.
1 paper.