Fooling LIME and SHAP

Dylan Slack; Sophie Hilgard; Emily Jia; Sameer Singh; Himabindu Lakkaraju; Dylan Slack University of California; Irvine; Irvine; CA; USA; Sophie Hilgard Harvard University; Cambridge; MA; USA; Emily Jia Harvard University; Cambridge; MA; USA; Sameer Singh University of California; Irvine; Irvine; CA; USA; Himabindu Lakkaraju Harvard University; Cambridge; MA; USA

doi:10.1145/3375627.3375830

Fooling LIME and SHAP

Dylan Slack, Sophie Hilgard, Emily Jia, Sameer Singh, Himabindu Lakkaraju, Dylan Slack University of California, Irvine, Irvine, CA, USA, Sophie Hilgard Harvard University, Cambridge, MA, USA, Emily Jia Harvard University, Cambridge, MA, USA, Sameer Singh University of California, Irvine, Irvine, CA, USA, Himabindu Lakkaraju Harvard University, Cambridge, MA, USA

Published: 4 February 2020

by ACM

in Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society

Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society ; doi:10.1145/3375627.3375830

Publisher Website

Google Scholar

Show/hide abstract

The publisher has not yet granted permission to display this abstract.

Keywords: Bias Detection / Adversarial Attacks / Model Interpretability / black box explanations