Scholar
Jaechul Roh
Google Scholar ID: knCeRjsAAAAJ
University of Massachusetts Amherst
Citations & Impact
Citations
81
H-index
5
i10-index
2
Publications
15
Co-authors
16
list available
Publications
Resume (English only)
Academic Achievements
- Published several papers, including 'SPILLage: Agentic Oversharing on the Web', 'Throttling Web Agents Using Reasoning Gates', and 'Bob's Confetti: Phonetic Memorization Attacks in Music and Video Generation'. Some of these papers have been accepted to conferences such as NeurIPS 2024 and USENIX Security 2025.
Research Experience
- Completed a Summer Research Internship at Brave Software, working on the privacy and security of AI agents with Ali Shahin Shamsabadi. During his undergraduate studies, he collaborated with Minhao Cheng on the robustness of language models, specifically exploring methods for defending against backdoor attacks in language models.
Education
- Pursuing a Ph.D. in Computer Science at the University of Massachusetts Amherst since August 2023, advised by Amir Houmansadr; earned a Bachelor of Engineering in Computer Engineering from the Hong Kong University of Science and Technology (HKUST) in May 2023, where he completed his Final Year Thesis (FYT) on 'Adversarial Attacks in Federated Learning' under the supervision of Jun Zhang.
Background
- PhD student in Computer Science, with research interests in the privacy and security of AI models and agentic systems, particularly focusing on understanding and mitigating vulnerabilities in multimodal systems.
