secure AI

Event Status: Cancelled | Towards Trustworthy Acceleration for AI Systems

Yuchen Yang, Assistant Professor, Privacy and Cybersecurity Informatics, The Pennsylvania State University (PSU)

Oct 22, 12:00 - 13:00

B4 R5209

Trustworthy AI Efficient AI accelerators trustworthy machine learning privacy-preserving AI Security and Privacy secure AI secure system design

In this talk, I will show how inference acceleration can not only weaken safety and security but also become a tool for attackers, and how these findings guide secure system design.

Egor Shulgin

Ph.D. Student, Computer Science

machine learning optimization Federated learning privacy-preserving AI secure AI

Egor Shulgin research investigates heterogeneous, efficient, and personalized federated learning, and practical optimizers for modern deep learning.