Post-Hoc Explanations Fail to Achieve their Purpose in Adversarial Contexts-Reference-Cited by-同舟云学术

Post-Hoc Explanations Fail to Achieve their Purpose in Adversarial Contexts

Published:2022-06-20 Issue: Volume: Page:
ISSN:
Container-title:2022 ACM Conference on Fairness, Accountability, and Transparency
language:
Short-container-title:

Author:

Bordt Sebastian¹,Finck Michèle²,Raidl Eric³,von Luxburg Ulrike¹

Affiliation:

1. Department of Computer Science, University of Tübingen, Germany

2. Law Faculty, University of Tübingen, Germany

3. Ethics and Philosophy Lab, University of Tübingen, Germany

Publisher

ACM

Link

https://dl.acm.org/doi/pdf/10.1145/3531146.3533153

Reference64 articles.

1. P. Achinstein . 1983. The Nature of Explanation . Oxford University Press , New York . P. Achinstein. 1983. The Nature of Explanation. Oxford University Press, New York.

2. Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)

3. J. Adebayo J. Gilmer M. Muelly I. Goodfellow M. Hardt and B. Kim. 2018. Sanity checks for saliency maps. In Neural Information Processing Systems (NeurIPS). J. Adebayo J. Gilmer M. Muelly I. Goodfellow M. Hardt and B. Kim. 2018. Sanity checks for saliency maps. In Neural Information Processing Systems (NeurIPS).

4. A.Karimi G. Barthe B. Schölkopf and I. Valera. 2021. A survey of algorithmic recourse: definitions formulations solutions and prospects. arxiv:2010.04050 A.Karimi G. Barthe B. Schölkopf and I. Valera. 2021. A survey of algorithmic recourse: definitions formulations solutions and prospects. arxiv:2010.04050

5. C. Anders , P. Pasliev , A. K. Dombrowski , K. R. Müller , and P. Kessel . 2020. Fairwashing explanations with off-manifold detergent . In International Conference on Machine Learning (ICML). C. Anders, P. Pasliev, A. K. Dombrowski, K. R. Müller, and P. Kessel. 2020. Fairwashing explanations with off-manifold detergent. In International Conference on Machine Learning (ICML).

Cited by 16 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Why Is the Current XAI Not Meeting the Expectations?;Communications of the ACM;2023-11-17

2. In-Training Explainability Frameworks: A Method to Make Black-Box Machine Learning Models More Explainable;2023 IEEE International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT);2023-10-26

3. Inherently interpretable position-aware convolutional motif kernel networks for biological sequencing data;Scientific Reports;2023-10-11

4. Through the looking glass: evaluating post hoc explanations using transparent models;International Journal of Data Science and Analytics;2023-09-12

5. A Means-End Account of Explainable Artificial Intelligence;Synthese;2023-07-17