This is the front page of Xiang Cheng’s webpage. I am a Research Scientist at Meta, working on ads ranking team, especially for LLM with content understanding and graph learning.
I recently completed my Ph.D. in Computer Science from the Georgia Institute of Technology, where my doctoral research, conducted in the SSLab, focused on Rust, program analsis and LLM for code under the guidance of Dr. Taesoo Kim since 2021. Before that, I am happy to work with Dr. David Devesery.
Prior to my Ph.D., I completed my Master’s at Georgia Tech and my undergraduate studies at Nanjing University. I enjoy leveraging my academic background to tackle real-world system challenges at scale.
Xiang Cheng, Fan Sang, Yibin Yang, Hang Zhang, Sangdon Park, Xiaokuan Zhang and Taesoo Kim. The Illusion of Rust Safety: Detecting Modular Unsafe Functions with LLMs. In Proceedings of the 28th ACM Conference on Computer and Communications Security (CCS), 2026
Xiang Cheng*, Sangdon Park*, HyungSeok Han, Xiaokuan Zhang and Taesoo Kim. Ruby: Unmasking Unsafe Rust in Stripped Binaries via Machine Learning. In Proceedings of the 56th Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN), 2026
Changho Choi, Xiang Cheng, Bokdeuk Jeong, and Taesoo Kim. Detecting inconsistencies in arm cca’s formally verified specification. In Proceedings of the 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), 2026
Sujin Park, Mingyu Guan, Xiang Cheng, and Taesoo Kim. Principles and Methodologies for Serial Performance Optimization. In Proceedings of the 19th USENIX Symposium on Operating Systems Design and Implementation (OSDI), July 2025
Xiang Cheng, Fan Sang, Yizhuo Zhai, Xiaokuan Zhang, and Taesoo Kim. RUG: Turbo LLM for Rust Unit Test Generation. In Proceedings of the 47th International Conference on Software Engineering (ICSE), Ottawa, Canada, April 2025
Scott Constable, Jo Van Bulck, Xiang Cheng, Yuan Xiao, Cedric Xing, Ilya Alexandrovich, Taesoo Kim, Frank Piessens, Mona Vij, and Mark Silberstein. {AEX-Notify}: Thwarting precise {Single-Stepping} attacks through interrupt awareness for intel {SGX} enclaves. In 32nd USENIX Security Symposium (USENIX Security 23), pages 4051–4068, 2023
Xiang Cheng and David Devecsery. Creating concise and efficient dynamic analyses with alda. In Proceedings of the 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), pages 740–752, 2022
Peng Li, Xiang Cheng, Xu Chu, Yeye He, and Surajit Chaudhuri. Auto-fuzzyjoin: auto-program fuzzy similarity joins without labeled examples. In Proceedings of the 2021 International Conference on Management of Data, pages 1064–1076, 2021