Are Objective Explanatory Evaluation metrics Trustworthy? An Adversarial Analysis
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911914212196352 |
|---|---|
| author | Chowdhury, Prithwijit Prabhushankar, Mohit AlRegib, Ghassan Deriche, Mohamed |
| author_facet | Chowdhury, Prithwijit Prabhushankar, Mohit AlRegib, Ghassan Deriche, Mohamed |
| contents | Explainable AI (XAI) has revolutionized the field of deep learning by empowering users to have more trust in neural network models. The field of XAI allows users to probe the inner workings of these algorithms to elucidate their decision-making processes. The rise in popularity of XAI has led to the advent of different strategies to produce explanations, all of which only occasionally agree. Thus several objective evaluation metrics have been devised to decide which of these modules give the best explanation for specific scenarios. The goal of the paper is twofold: (i) we employ the notions of necessity and sufficiency from causal literature to come up with a novel explanatory technique called SHifted Adversaries using Pixel Elimination(SHAPE) which satisfies all the theoretical and mathematical criteria of being a valid explanation, (ii) we show that SHAPE is, infact, an adversarial explanation that fools causal metrics that are employed to measure the robustness and reliability of popular importance based visual XAI methods. Our analysis shows that SHAPE outperforms popular explanatory techniques like GradCAM and GradCAM++ in these tests and is comparable to RISE, raising questions about the sanity of these metrics and the need for human involvement for an overall better evaluation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_07820 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Are Objective Explanatory Evaluation metrics Trustworthy? An Adversarial Analysis Chowdhury, Prithwijit Prabhushankar, Mohit AlRegib, Ghassan Deriche, Mohamed Computer Vision and Pattern Recognition Machine Learning Explainable AI (XAI) has revolutionized the field of deep learning by empowering users to have more trust in neural network models. The field of XAI allows users to probe the inner workings of these algorithms to elucidate their decision-making processes. The rise in popularity of XAI has led to the advent of different strategies to produce explanations, all of which only occasionally agree. Thus several objective evaluation metrics have been devised to decide which of these modules give the best explanation for specific scenarios. The goal of the paper is twofold: (i) we employ the notions of necessity and sufficiency from causal literature to come up with a novel explanatory technique called SHifted Adversaries using Pixel Elimination(SHAPE) which satisfies all the theoretical and mathematical criteria of being a valid explanation, (ii) we show that SHAPE is, infact, an adversarial explanation that fools causal metrics that are employed to measure the robustness and reliability of popular importance based visual XAI methods. Our analysis shows that SHAPE outperforms popular explanatory techniques like GradCAM and GradCAM++ in these tests and is comparable to RISE, raising questions about the sanity of these metrics and the need for human involvement for an overall better evaluation. |
| title | Are Objective Explanatory Evaluation metrics Trustworthy? An Adversarial Analysis |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2406.07820 |