Explainable Artificial Intelligence: Importance, Use Domains, Stages, Output Shapes, and Challenges
There is an urgent need in many application areas for eXplainable ArtificiaI Intelligence
(XAI) approaches to boost people's confidence and trust in Artificial Intelligence methods …
(XAI) approaches to boost people's confidence and trust in Artificial Intelligence methods …
Fooling SHAP with Output Shuffling Attacks
J Yuan, A Dasgupta - arXiv preprint arXiv:2408.06509, 2024 - arxiv.org
Explainable AI~(XAI) methods such as SHAP can help discover feature attributions in black-
box models. If the method reveals a significant attribution from a``protected feature''(eg …
box models. If the method reveals a significant attribution from a``protected feature''(eg …
A Simple Scoring Function to Fool SHAP: Stealing from the One Above
J Yuan, A Dasgupta - XAI in Action: Past, Present, and Future Applications - openreview.net
Explainable Al (XAl) methods such as SHAP can help discover unfairness in black-box
models. If the XAl method reveals a significant impact from a" protected attribute"(eg, gender …
models. If the XAl method reveals a significant impact from a" protected attribute"(eg, gender …