Loading Events

ASSET Seminar: “Towards Trustworthy AI: Automated Interpretability, Adversarial Robustness, and AI safety”

November 4 at 12:00 PM - 1:00 PM
Virtual Event
Details
Date: November 4, 2026
Time: 12:00 PM - 1:00 PM
Event Category: Seminar
Event Tags:
Organizer
AI-enabled Systems: Safe, Explainable, and Trustworthy (ASSET) Center
asset-info@seas.upenn.edu
View Website
Venue
Amy Gutmann Hall, Room 414 3333 Chestnut Street
Philadelphia
19104
Google Map

Deep learning models have become remarkably powerful – but often operate as black boxes. In this talk, I will share a series of work from my lab on how to make these systems more transparent, reliable, and trustworthy. I’ll highlight three research directions to bring interpretability into deep learning: (1) automated tools [1-7] that reveal what neural networks learn internally at scale and enable behavioral control; (2) inherently interpretable neural model architectures [8-13] that make model’s decision process more understandable and controllable; and (3) evaluation frameworks [14-16] that quantify interpretability and enable trust. I’ll also touch on our work [17-22] in jailbreak attacks on LLMs, LLM agent safety, robustness verification, and robust learning for safer AI deployment. Together, these efforts aim to move modern AI beyond accuracy – toward systems we can truly understand, align, and trust. For more details, please visit https://lilywenglab.github.io/.

Watch the Seminar Recording!

Speaker

Lily Weng

Assistant Professor, UCSD

Lily Weng is an Assistant Professor in the Halıcıoğlu Data Science Institute at UC San Diego and she leads the Trustworthy Machine Learning Lab at UC San Diego. She received her PhD in Electrical Engineering and Computer Science (EECS) from MIT in August 2020, and her Bachelor and Master degree both in Electrical Engineering at National Taiwan University. Prior to UCSD, she spent 1 year in MIT-IBM Watson AI Lab and several research internships in Google DeepMind, IBM Research and Mitsubishi Electric Research Lab. Her research interest is in machine learning and deep learning, with primary focus on Trustworthy AI. Her vision is to make the next generation AI systems and deep learning algorithms more robust, reliable, explainable, trustworthy and safer. Her work has been recognized and supported by multiple NSF awards, ARL award, DARPA awards, Intel Rising Star Faculty Award, Hellman Fellowship, and Nvidia Academic award. For more details, please see https://lilywenglab.github.io/.