UT Austin Computer Architecture Seminar Series 2025 Spring
Sponsored by:
| Date | Series | Topic | Speaker |
| January 24, 2025 | Series 01 | Securing Computer Systems using AI Methods and for AI Applications | Mulong Luo |
2025 Spring Semester
Sponsored by:
[Series 01] Securing Computer Systems using AI Methods and for AI Applications
Title: Securing Computer Systems using AI Methods and for AI Applications
Speaker: Mulong Luo, Postdoctoral Researcher, UT ECE
Date: Friday January 24, 2025, 3:30pm
Location: EER 0.806/0.808 or Zoom Link
Abstract:
Securing modern computer systems against an ever-evolving threat landscape is a significant challenge that requires innovative approaches. Recent developments in artificial intelligence (AI), such as large language models (LLMs) and reinforcement learning (RL), have achieved unprecedented success in everyday applications. However, AI serves as a double-edged sword for computer systems security. On one hand, the superhuman capabilities of AI enable the exploration and detection of vulnerabilities without the need for human experts. On the other hand, specialized systems required to implement new AI applications introduce novel security vulnerabilities.
In this talk, I will first present my work on applying AI methods to system security. Specifically, I leverage reinforcement learning to explore microarchitecture attacks in modern processors. Additionally, I will discuss the use of multi-agent reinforcement learning to improve the accuracy of detectors against adaptive attackers. Next, I will highlight my research on the security of AI systems, focusing on retrieval-augmented generation (RAG)-based LLMs and autonomous vehicles. For RAG-based LLMs, my ConfusedPilot work demonstrates how an attacker can compromise confidentiality and integrity guarantees by sharing a maliciously crafted document. For autonomous vehicles, I reveal a software-based cache side-channel attack capable of leaking the physical location of a vehicle without detection. Finally, I will outline future directions for building secure systems using AI methods and ensuring the security of AI systems.
Bio:
Mulong Luo is currently a postdoctoral researcher at the University of Texas at Austin hosted by Mohit Tiwari. His research interests lie broadly in applying AI methods for computer architecture and system security, as well as improving the security of AI systems including LLM and autonomous vehicles. He is selected as a CPS Rising Star 2023. His paper is selected as a finalist in Top Picks in Hardware and Embedded Security 2022. He is also awarded the best paper award at CPS-SPC 2018. Mulong received Ph.D. at Cornell University advised by Edward Suh in 2023. He got his MS and BS from UCSD and Peking University respectively.