Talks

Guest Lectures

• (2023 Spring) CMU 18661 - Explaining and Assessing Feature Alignment in Vision Models

• (2023 Fall) Standford CS 329T - Universal and Transferable Attacks to Algined Language Models

Tutorials

• (AAAI-21) From Explainability to Robustness, and Back Again

• (KDD 2022) Machine Learning Explainability and Robustness: Connected At Hip