Jaylen Jones

Jaylen Jones

he/him/his

CSE PhD Student @ The Ohio State University

About Me

Hi, I’m Jaylen Jones, a third-year PhD student in Computer Science & Engineering at The Ohio State University (OSU) advised by Prof. Huan Sun and Prof. Eric Fosler-Lussier. Prior to joining OSU, I received my B.S. in Computer Science from the College of Informatics at Northern Kentucky University (NKU).

🚀 Seeking a research internship for Summer 2026, feel free to reach out if you have any opportunities!

Research Interests

My research centers on AI with a focus in natural language processing, the alignment of large language models (LLMs) to human values, and LLM-based agents. I am particularly interested in the design, evaluation, and applications of LLM-based systems for high-stakes, human-centered applications, unlocking the full potential of AI capabilities while ensuring the trustworthiness, robustness, and safety required for real-world use.

My current work focuses on the following high-level area:

  • Evaluating and mitigating the risks of computer-use agents, with an emphasis on both security (i.e., protecting agents from adversarial attack) and safety (i.e., preventing accidental agent harms emerging from typical benign inputs).

Publications & Papers

  • RedTeamCUA: Towards Realistic Adversarial Testing of CUAs in Hybrid Web-OS Environments (Oral)
    Paper · Website · Code
    Zeyi Liao*, Jaylen Jones*, Linxi Jiang*, Eric Fosler-Lussier, Yu Su, Zhiqiang Lin, Huan Sun
    (* denotes equal contribution)
    The Fourteenth International Conference on Learning Representations
    (ICLR 2026)

  • When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents
    Paper · Website · Code · Data
    Jaylen Jones*, Zhehao Zhang*, Yuting Ning, Eric Fosler-Lussier, Pierre-Luc St-Charles, Yoshua Bengio, Dawn Song, Yu Su, Huan Sun
    (* denotes equal contribution)
    (arXiv 2026)

  • When Actions Go Off-Task: Detecting and Correcting Misaligned Actions in Computer-Use Agents
    Paper · Website · Code · Data
    Yuting Ning, Jaylen Jones, Zhehao Zhang, Chentao Ye, Weitong Ruan, Junyi Li, Rahul Gupta, Huan Sun
    (arXiv 2026)

  • AmpleGCG-Plus: A Strong Generative Model of Adversarial Suffixes to Jailbreak LLMs with Higher Success Rates in Fewer Attempts
    Paper
    Vishal Kumar, Zeyi Liao, Jaylen Jones, Huan Sun
    (arXiv 2025)

  • A Multi-Aspect Framework for Counter Narrative Evaluation using Large Language Models
    Paper
    Jaylen Jones, Lingbo Mo, Eric Fosler-Lussier, Huan Sun
    2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics
    (NAACL 2024)

Awards and Experience