Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods
Authors: Dylan Slack, Sophie Hilgard, Emily Jia, Sameer Singh, Himabindu Lakkaraju | Published: 2019-11-06 | Updated: 2020-02-03
説明可能性に対する攻撃
Explanations can be manipulated and geometry is to blame
Authors: Ann-Kathrin Dombrowski, Maximilian Alber, Christopher J. Anders, Marcel Ackermann, Klaus-Robert Müller, Pan Kessel | Published: 2019-06-19 | Updated: 2019-09-25
Interpretation of Neural Networks is Fragile
Authors: Amirata Ghorbani, Abubakar Abid, James Zou | Published: 2017-10-29 | Updated: 2018-11-06