Don't Lie to Me: Avoiding Malicious Explanations with STEALTH

25 January 2023

Papers citing "Don't Lie to Me: Avoiding Malicious Explanations with STEALTH"

3 / 3 papers shown

Title
Unfooling Perturbation-Based Post Hoc Explainers Zachariah Carmichael Walter J. Scheirer AAML 42 14 0 29 May 2022
FairMask: Better Fairness via Model-based Rebalancing of Protected Attributes Kewen Peng Joymallya Chakraborty Tim Menzies FaML 29 27 0 03 Oct 2021
Can I Trust My Fairness Metric? Assessing Fairness with Unlabeled Data and Bayesian Inference Disi Ji Padhraic Smyth M. Steyvers 34 43 0 19 Oct 2020