Yanzuo Chen

ychenjo@cse.ust.hk

I am a fourth-year PhD student in Computer Science and Engineering at the Hong Kong University of Science and Technology (HKUST), supervised by Prof. Shuai Wang. Before that, I received my B.Eng. degree in Computer Science and Engineering from the Chinese University of Hong Kong, Shenzhen in 2021.

I do research in Systems Security and have published a few papers where we look at ML and AI security from systems/infrastructure perspectives. I leave the door open while working so I also have other ongoing projects on topics that intrigue me. Ultimately, I want my research to protect the people and the systems they depend on.

I am a maintainer of the Rclone project, and was a Google Summer of Code participant with the Matrix Foundation. Fan of Undertale, The Impossible Trial, and Akiyama Mizuki. I speak Cantonese and Mandarin natively. I have working knowledge of English and non-working knowledge of Japanese :)

Education

Selected Publications

• BitShield: Defending Against Bit-Flip Attacks on DNN Executables.
  Yanzuo Chen, Yuanyuan Yuan, Zhibo Liu, Sihang Hu, Tianxiang Li, and Shuai Wang.
  In NDSS 2025. (Prepublication)
• Compiled Models, Built-In Exploits: Uncovering Pervasive Bit-Flip Attack Surfaces in DNN Executables.
  Yanzuo Chen, Zhibo Liu, Yuanyuan Yuan, Sihang Hu, Tianxiang Li, and Shuai Wang.
  In NDSS 2025. (Prepublication)
• CipherSteal: Stealing Input Data from TEE-Shielded Neural Networks with Ciphertext Side Channels.
  Yuanyuan Yuan, Zhibo Liu, Sen Deng, Yanzuo Chen, Shuai Wang, Yinqian Zhang, and Zhendong Su.
  In IEEE S&P 2025. (Prepublication)
• The Devil is in the (Micro-) Architectures: Uncovering New Side-Channel and Bit-Flip Attack Surfaces in DNN Executables.
  Yanzuo Chen, Zhibo Liu, Yuanyuan Yuan, Sihang Hu, Tianxiang Li, and Shuai Wang.
  In Black Hat Europe 2024. (Abstract|Companion)
• DeepCache: Revisiting Cache Side-Channel Attacks in Deep Neural Networks Executables.
  Zhibo Liu, Yuanyuan Yuan, Yanzuo Chen, Sihang Hu, Tianxiang Li, and Shuai Wang.
  In CCS 2024. (Prepublication)
• HyperTheft: Thieving Model Weights from TEE-Shielded Neural Networks via Ciphertext Side Channels.
  Yuanyuan Yuan, Zhibo Liu, Sen Deng, Yanzuo Chen, Shuai Wang, Yinqian Zhang, and Zhendong Su.
  In CCS 2024. (Prepublication)
• OBSan: An Out-Of-Bound Sanitizer to Harden DNN Executables.
  Yanzuo Chen, Yuanyuan Yuan, and Shuai Wang.
  In NDSS 2023. (Paper|Code|Talk)

Teaching

Academic Services

Artifact Evaluation Committee Member

• NDSS 2024, USENIX Security 2024

External Reviewer

• USENIX Security 2024, IEEE S&P 2024, CCS 2023, CCS 2022, ASE 2022, AsiaCCS 2022

Honours