AttEXplore: Attribution for Explanation with model parameters eXploration

Zhiyu Zhu, Huaming Chen, Jiayu Zhang, Xinyi Wang, Zhibo Jin, Jason Xue, Flora D. Salim

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: attribution, transferability, adversarial attack

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

Abstract: Due to the real-world noise and human-added perturbations, attaining the trustworthiness of deep neural networks (DNNs) is a challenging task. Therefore, it becomes essential to offer explanations for the decisions made by these non-linear and complex parameterized models. Attribution methods are promising for this goal, yet its performance can be further improved. In this paper, for the first time, we present that the decision boundary exploration approaches of attribution are consistent with the process for transferable adversarial attacks. Specifically, the transferable adversarial attacks craft general adversarial samples from the source model, which is consistent with the generation of adversarial samples that can cross multiple decision boundaries in attribution. Utilizing this consistency, we introduce a novel attribution method via model parameter exploration. Furthermore, inspired by the capability of frequency exploration to investigate the model parameters, we provide enhanced explainability for DNNs by manipulating the input features based on frequency information to explore the decision boundaries of different models. Large-scale experiments demonstrate that our \textbf{A}ttribution method for \textbf{E}xplanation with model parameter e\textbf{X}ploration (AttEXplore) outperforms other state-of-the-art interpretability methods. Moreover, by employing other transferable attack techniques, AttEXplore can explore potential variations in attribution outcomes. Our code is available at: https://github.com/LMBTough/ATTEXPLORE.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Primary Area: visualization or interpretation of learned representations

Submission Number: 5047