Beijie Liu

Ph.D. Student
University of Southern California
beijieli (at)usc.edu

About Me

I am a second-year Ph.D. student in Computer Science at the University of Southern California, advised by Prof. Mengyuan Li. I received my Bachelor’s degree from Shanghai Jiao Tong University.

Previously, I worked as a student researcher at the University of Michigan in OrderLab, supervised by Ryan Huang, and in CHAI Lab, supervised by Emily Mower Provost.

My research interests lie broadly in LLM Security and Systems for ML.

Education

Ph.D. in Computer Science, University of Southern California (2025 - present)
B.E. in Electrical and Computer Engineering, Shanghai Jiao Tong University (2021 - 2025)
B.E. in Computer Science, University of Michigan (2023 - 2025)

News

[Mar. 2025] Our paper Hollow LLM is accepted to S&P 2026.
[Dec. 2025] Our paper WAVE is accepted to ASPLOS 2026.
[Sept. 2025] I joined the Sept Lab at USC as a Ph.D. student.
[Mar. 2025] Our work Training with Confidence is accepted to OSDI 2025.
[Sep. 2024] I was a TA in the course EECS 445: Machine Learning at Umich.

Publications

S&P

Hollow-LLM Attack: Computationally Trivial Weights in Zero-Knowledge Verification of LLM Inference

Chen Gong, Beijie Liu, Mengyuan Li

IEEE Symposium on Security and Privacy (S&P), 2026.

PDF Code Project Page BibTex Accepted

ASPLOS

Wave: Leveraging Architecture Observation for Privacy-Preserving Model Oversight

Haoxuan Xu*, Chen Gong*, Beijie Liu*, Haizhong Zheng, Beidi Chen, Mengyuan Li (*Equal contribution)

ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), 2026.

PDF Code Project Page BibTex Accepted

OSDI

Training with Confidence: Catching Silent Errors in Deep Learning Training with Automated Proactive Checks

Yuxuan Jiang, Ziming Zhou, Boyu Xu, Beijie Liu, Runhui Xu, Peng Huang

19th USENIX Symposium on Operating Systems Design and Implementation (OSDI '25), 2025.

PDF Code Project Page BibTex Accepted

Powered by Jekyll and Minimal Light theme.