Skip to main content
← Back to seminars

Past talk · AI/ML Seminar Series

Exposing Shortcomings and Improving the Reliability of Machine Learning Explanations

Dylan Slack

PhD Student, Department of Computer Science, University of California, Irvine

Date & time
Monday, January 31, 2022 · 1:00 PM
Location
Online (live stream)

Abstract

For domain experts to adopt machine learning models in high-stakes settings such as health care and law, they must understand and trust model predictions. Researchers have proposed numerous ways to explain complex ML models, but these approaches suffer from critical drawbacks such as vulnerability to adversarial attacks, instability, and inconsistency. This talk describes the shortcomings of explanations, demonstrates how they are vulnerable to adversarial attacks, and presents recent work on explanations that leverage uncertainty estimates to overcome several critical explanation shortcomings.

About the speaker

Dylan Slack is a Ph.D. candidate at UC Irvine advised by Sameer Singh and Hima Lakkaraju. His research focuses on developing techniques that help build more robust, reliable, and trustworthy machine learning models. He has held research internships at Google AI and Amazon AWS and was previously an undergraduate at Haverford College.