University of California, Los Angeles
Portrait of Ying Li

Ying Li

Ph.D. Candidate · Electrical & Computer Engineering · UCLA

Hi, this is Ying Li. I'm a Ph.D. candidate in the ECE department at UCLA, working with Prof. Yuan Tian. I received my B.E. in Cybersecurity from the School of Cyber Science and Engineering, Sichuan University. I was a Research Assistant at The Chinese University of Hong Kong (CUHK).

My research focuses on the security of AI agents and modern software systems, specifically: (1) neurosymbolic reasoning and agentic RL for secure code and privacy, from detecting and automatically patching violations to training models that avoid introducing them; (2) benchmarks for agent security, measuring how deployed agents actually fail in areas such as vulnerability patching, authorization, and prompt injection; and (3) formal methods and security for AI agents, ensuring autonomous systems behave safely and correctly through formal verification and runtime guarantees. My work has been adopted or acknowledged by Amazon, NVIDIA, Microsoft, and Qwen, among others. My research is generously supported by UCLA’s Samueli Fellowship.

Email Google Scholar LinkedIn X / Twitter

🧭 I am actively seeking 2027 research internship opportunities in LLM agent security, safety, and alignment.

News

Selected Publications

Google Scholar

* denotes equal contribution

  1. NeurIPS 2026 MetaPI: Constructing Prompt Injection Benchmarks from Any Agent Benchmarks

    Peiran Wang*, Chong Xiang*, Wenjie Qu, Ying Li, Jiaheng Zhang, G. Edward Suh, and Yuan Tian

  2. ASE 2026 · Industry From Security Findings to Verified Fixes: Automated Repair of Infrastructure-as-Code Misconfigurations

    Ying Li, Tamjid Rahat, Yingjun Lyu, Omer Tripp, and George Argyros

  3. IEEE S&P 2026 Breaking the Illusion: Automated Reasoning of GDPR Consent Violations

    Ying Li, Wenjun Qiu, Faysal Hossain Shezan, Kunlin Cai, Michelangelo van Dam, Lisa Austin, David Lie, and Yuan Tian

  4. PoPETs 2026 Location-Enhanced Information Flow for Home Automations

    McKenna McCall, Ben Weinshel, Kunlin Cai, Ying Li, Eric Zeng, Devika Manohar, Lujo Bauer, Limin Jia, and Yuan Tian

  5. NDSS 2026 From Perception to Protection: A Developer-Centered Study of Security and Privacy Threats in Extended Reality (XR)

    Kunlin Cai, Jinghuai Zhang, Ying Li, Zhiyuan Wang, Xun Chen, Tianshi Li, and Yuan Tian

Recent Preprints

  1. arXiv 2026 VIGIL: Runtime Enforcement of Behavioral Specifications in AI Agent Skills

    Ying Li, Yanju Chen, Hongbo Wen, Bosi Zhang, Hanzhi Liu, Peiran Wang, Yu Feng, and Yuan Tian

    Paper

  2. arXiv 2026 No Attack Required: Semantic Fuzzing for Specification Violations in Agent Skills

    Ying Li, Hongbo Wen, Yanju Chen, Hanzhi Liu, Yuan Tian, and Yu Feng

    Paper

  3. arXiv 2026 Options, Not Clicks: Lattice Refinement for Consent-Driven MCP Authorization

    Ying Li, Yanju Chen, Peiran Wang, Issac Khabra, Faysal Hossain Shezan, Yu Feng, and Yuan Tian

    Paper

  4. arXiv 2026 Semia: Auditing Agent Skills via Constraint-Guided Representation Synthesis

    Hongbo Wen, Ying Li, Hanzhi Liu, Chaofan Shou, Yanju Chen, Yuan Tian, and Yu Feng

    Paper

  5. arXiv 2026 The Landscape of Prompt Injection Threats in LLM Agents: From Taxonomy to Analysis

    Peiran Wang, Xinfeng Li, Chong Xiang, Jinghuai Zhang, Ying Li, Lixia Zhang, Xiaofeng Wang, and Yuan Tian

    Paper

Awards & Honors

Employment

Services

Misc

my cats