Seminars and Events

Artificial Intelligence Seminar

Towards Socially Responsible Machine Learning: Security, Robustness, and Beyond

Event Details

Deep Learning (DL) has achieved great success in recent years, with its applications being used in many real-world applications, even in safety-critical situations. Despite this, the question remains: is DL ready for widespread use? In this talk, we will explore the socially responsible issues of current DL systems from the perspectives of security, robustness, and beyond.

The talk will start by discussing the security threats posed by current DL systems in the worst-case adversarial setting. We will introduce a purification-based method to enhance adversarial robustness without the need for additional adversarial training. Then, we will move on to a more general setting, discussing robustness against covariate shift and exploring ways to improve model robustness. Finally, we will touch upon the challenges and opportunities posed by socially responsible problems in the era of foundational models, beyond security and robustness.

YOU ONLY NEED TO REGISTER ONCE TO ATTEND THE ENTIRE SERIES – We will send you email announcements with details of the upcoming speakers.

Register in advance for this webinar:

After registering, you will receive an email confirmation containing information about joining the Zoom webinar.

The Speaker approved to be recorded for this AI Seminar talk, it will be posted on our USC/ISI YouTube page within 1-2 business days:

Host: Muhao Chen, POC: Maura Covaci

Speaker Bio

Chaowei Xiao is an Assistant Professor at Arizona State University. He received his B.E. degree in the School of Software from Tsinghua University in 2015 and his Ph.D. degree in the Computer Science Department from the University of Michigan, Ann Arbor in 2020. His research interests lie in the intersection of security, privacy, and machine learning. Dr. Xiao's work has been featured in multiple media outlets, including Wired, Fortune, and IEEE SPECTRUM. One of his research outputs is on display at the London Science Museum. He has received the ACM Gordon Bell Special Prize for COVID-19 Research and multiple best paper awards.