Shapley Ensemble Adversarial Attack
Lists
Only you see this
Abstract
An intuitive strategy for generating more transferable adversarial examples is to absorb the advantages of different surrogates in an ensemble. However, existing ensemble adversarial attacks simply average the outputs of various models while ignoring their different contributions. To quantify the importance of various surrogates, we propose a novel Shapley Ensemble Adversarial Attack (dubbed SEAA) – an effective algorithm that allocates weights based on Shapley values of the surrogates. Specifically, the synthesis of adversarial examples in an ensemble adversarial attack is firstly regarded as a cooperative game process of multiple surrogates from the perspective of contribution. As the Shapley value is known as an effective decision metric in cooperative game theory, it is thus intuitively introduced into this work to accurately evaluate the contribution of a surrogate by reweighing its importance at each iteration, thus avoiding local optimality and steering the generation of adversarial examples. Comprehensive experimental results demonstrate our effectiveness.
BibTeX
@inproceedings{wang2024shapley,
author = {Zheng Wang and Bowen Tang and Yi Bin and Lei Zhu and Guoqing Wang and Yang Yang},
title = {{Shapley Ensemble Adversarial Attack}},
booktitle = {ICME},
year = {2024},
doi = {10.1109/icme57554.2024.10687833},
}Loading related content...