Xinhang (Owen) Ma

Ph.D. Student
Computer Science & Engineering, Washington University in St. Louis

About

I am a Ph.D. student in the Department of Computer Science & Engineering at Washington University in St. Louis, advised by Prof. Yevgeniy Vorobeychik. My research interests lie in AI agents and LLM security and protection.

Publications

  1. ROPE: Routed Origin Policy Enforcement against Indirect Prompt Injection

    Xinhang Ma, Chaowei Xiao, William Yeoh, Ning Zhang, Yevgeniy Vorobeychik

    arXiv preprint, 2026 arXiv Code

  2. Robust Context-Aware Detection of Malicious Instructions in Text

    Buzhao Liu*, Xinhang Ma*, Yevgeniy Vorobeychik (* equal contribution)

    arXiv preprint, 2026 arXiv Code

  3. AutoDojo: Adaptive Black-Box Attacks Reveal the Limits of IPI Defenses and Task-Specification Effects in LLM Agents

    Xinhang Ma, Taoran Li, Chaowei Xiao, Zhiyuan Yu, Ning Zhang, Yevgeniy Vorobeychik

    arXiv preprint, 2026 arXiv Code

  4. Protecting Language Models Against Unauthorized Distillation through Trace Rewriting

    Xinhang Ma, William Yeoh, Ning Zhang, Yevgeniy Vorobeychik

    ACL 2026, Main Conference arXiv Code

  5. Conformal Reachability for Safe Control in Unknown Environments

    Xinhang Ma, Junlin Wu, Yiannis Kantaros, Yevgeniy Vorobeychik

    AAMAS 2026 arXiv Code

  6. Learning Vision-Based Neural Network Controllers with Semi-Probabilistic Safety Guarantees

    Xinhang Ma, Junlin Wu, Hussein Sibai, Yiannis Kantaros, Yevgeniy Vorobeychik

    AAAI 2026 arXiv Code

  7. From Speech to Data: Unraveling Google's Use of Voice Data for User Profiling

    Xinhang Ma, Sirui Chen

    arXiv preprint, 2024 (not peer reviewed) arXiv Code

Service

Conference Reviewer