|
Hongyu Cai Hongyu Cai is a Ph.D. student in the Department of Computer Science at Purdue University. He works at the PurSec Lab under the supervision of Prof. Z. Berkay Celik. His research focuses on the security of foundation models and their applications. Prior to joining Purdue University, he earned a bachelor's degree from Northeastern University in Shenyang, China, in 2020. Email / Google Scholar / LinkedIn / GitHub / Zhihu |
|
Publications |
|
Words Speak Louder Than Code: Investigating Cognitive
Heuristics in LLM-Based Code Vulnerability
Detection
Asif Shahriar; Hongyu Cai; Hadjer Benkraouda; Gang Wang; Z. Berkay Celik IEEE Symposium on Security and Privacy (S&P), 2027 BibTeX / arXiv / code |
|
Reveree: Diagnosing LLM Reverse-Engineering Agents
Hadjer Benkraouda; Hongyu Cai; Z. Berkay Celik; Gang Wang arXiv: 2609.01185, 2026 BibTeX / arXiv |
|
RoboJailBench: Benchmarking Adversarial Attacks and
Defenses in Embodied Robotic Agents
Doguhuan Yeke; Yanming Zhou; Leo Y Lin; Hongyu Cai; Antonio Bianchi; Z. Berkay Celik arXiv: 2605.19328, 2026 BibTeX / arXiv |
|
Exploring and Developing a Pre-Model Safeguard with
Draft Models
Hongyu Cai; Arjun Arunasalam; Yiming Liang; Antonio Bianchi; Z. Berkay Celik ACM Conference on AI and Agentic Systems (CAIS), 2026 BibTeX / DOI / code |
|
D-LiFT: Improving LLM-based Decompiler Backend via Code
Quality-driven Fine-tuning
Muqi Zou; Hongyu Cai; Hongwei Wu; Zion Leonahenahe Basque; Arslan Khan; Z. Berkay Celik; Antonio Bianchi; Dongyan Xu arXiv: 2506.10125, 2025 BibTeX / arXiv |
|
Rethinking How to Evaluate Language Model Jailbreak
Hongyu Cai; Arjun Arunasalam; Leo Y Lin; Antonio Bianchi; Z. Berkay Celik ACM Workshop on Artificial Intelligence and Security (AISec), 2025 BibTeX / arXiv / code / package |
|
A Progressive Transformer for Unifying Binary Code
Embedding and Knowledge Transfer
Hanxiao Lu; Hongyu Cai; Yiming Liang; Antonio Bianchi; Z. Berkay Celik IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER), 2024 BibTeX / DOI |
|
Benchmark to Audit LLM Generated Clinical Notes for
Disparities Arising from Biases and Stereotypes
Hongyu Cai; Swetasudha Panda; Naveen Jafer Nizar; Qinlan Shen; Daeja Oxendine; Sumana Srivatsa; Krishnaram Kenthapadi Annual Conference on Neural Information Processing Systems (NeurIPS) - Workshop, 2024 BibTeX / poster |
|
NN-Baton: DNN Workload Orchestration and Chiplet
Granularity Exploration for Multichip Accelerators
Zhanhong Tan; Hongyu Cai; Runpei Dong; Kaisheng Ma ACM/IEEE Annual International Symposium on Computer Architecture (ISCA), 2021 BibTeX / DOI |
Education |
|
Purdue University, West Lafayette, USA,
Ph.D. Computer Science (2023 - Present)
University of Massachusetts Amherst,
Amherst, USA, Ph.D. Electrical and Computer Engineering
(2020 - 2023, transferred to Purdue University)
Northeastern University, Shenyang, China,
B.Eng. Computer Science and Technology (2016 - 2020)
|
Experience |
|
Oracle Labs, Research Assistant (Jun 2024 - Sep 2024), Burlington, USA
MiraclePlus, Industry Research (Jun 2024), formerly Y Combinator China
Intel Corporation, Internship (Jun 2022 - Sep 2022), Santa Clara, USA
Custom Compute Group; Homomorphic Encryption Accelerator
Tsinghua University, Research Assistant (Jun 2020 - Aug 2020), Beijing, China
Institute for Interdisciplinary Information Sciences
Microsoft Research Asia, Research Internship (Jul 2019 - Jun 2020), Beijing, China
Systems and Networking Research Group
|
|
This website is based on Jon Barron's public academic website. Do not scrape the HTML of this page, as it includes analytics tags that you do not want on your own website — use the GitHub repository instead. |
