Rethinking Robustness: A New Approach to Evaluating Feature Attribution Methods
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911306261463040 |
|---|---|
| author | Kiourti, Panagiota Singh, Anu Duraipandian, Preeti Zhou, Weichao Li, Wenchao |
| author_facet | Kiourti, Panagiota Singh, Anu Duraipandian, Preeti Zhou, Weichao Li, Wenchao |
| contents | This paper studies the robustness of feature attribution methods for deep neural networks. It challenges the current notion of attributional robustness that largely ignores the difference in the model's outputs and introduces a new way of evaluating the robustness of attribution methods. Specifically, we propose a new definition of similar inputs, a new robustness metric, and a novel method based on generative adversarial networks to generate these inputs. In addition, we present a comprehensive evaluation with existing metrics and state-of-the-art attribution methods. Our findings highlight the need for a more objective metric that reveals the weaknesses of an attribution method rather than that of the neural network, thus providing a more accurate evaluation of the robustness of attribution methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_06665 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Rethinking Robustness: A New Approach to Evaluating Feature Attribution Methods Kiourti, Panagiota Singh, Anu Duraipandian, Preeti Zhou, Weichao Li, Wenchao Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition This paper studies the robustness of feature attribution methods for deep neural networks. It challenges the current notion of attributional robustness that largely ignores the difference in the model's outputs and introduces a new way of evaluating the robustness of attribution methods. Specifically, we propose a new definition of similar inputs, a new robustness metric, and a novel method based on generative adversarial networks to generate these inputs. In addition, we present a comprehensive evaluation with existing metrics and state-of-the-art attribution methods. Our findings highlight the need for a more objective metric that reveals the weaknesses of an attribution method rather than that of the neural network, thus providing a more accurate evaluation of the robustness of attribution methods. |
| title | Rethinking Robustness: A New Approach to Evaluating Feature Attribution Methods |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.06665 |