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 for AI agent security and safety, ensuring autonomous systems behave 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
- Two papers accepted at ICSE 2027.
- Paper accepted at NeurIPS 2026, see you in Atlanta!
- Named a USENIX Security Noteworthy Artifact Reviewer.
- Paper accepted at ASE 2026.
- Led one of 10 teams selected for the Amazon Nova AI Challenge ($250K award).
Selected Publications
Google Scholar* denotes equal contribution
-
ICSE 2027 Automated Safety Analysis for Agentic Workflows
-
NeurIPS 2026 MetaPI: Constructing Prompt Injection Benchmarks from Any Agent Benchmarks
-
ASE 2026 · Industry From Security Findings to Verified Fixes: Automated Repair of Infrastructure-as-Code Misconfigurations
-
IEEE S&P 2026 Breaking the Illusion: Automated Reasoning of GDPR Consent Violations
-
PoPETs 2026 Location-Enhanced Information Flow for Home Automations
-
NDSS 2026 From Perception to Protection: A Developer-Centered Study of Security and Privacy Threats in Extended Reality (XR)
-
USENIX Security 2025 SoK: Towards Effective Automated Vulnerability Repair
-
WWW 2025 Detecting and Understanding the Promotion of Illicit Goods and Services on Twitter
-
USENIX Security 2023 CarpetFuzz: Automatic Program Option Constraint Extraction from Documentation for Fuzzing
-
CCS 2022 Clues in Tweets: Twitter-Guided Discovery and Analysis of SMS Spam
Recent Preprints
-
arXiv 2026 VIGIL: Runtime Enforcement of Behavioral Specifications in AI Agent Skills
-
arXiv 2026 No Attack Required: Semantic Fuzzing for Specification Violations in Agent Skills
-
arXiv 2026 Options, Not Clicks: Lattice Refinement for Consent-Driven MCP Authorization
-
arXiv 2026 Semia: Auditing Agent Skills via Constraint-Guided Representation Synthesis
-
arXiv 2026 The Landscape of Prompt Injection Threats in LLM Agents: From Taxonomy to Analysis
Awards & Honors
- Amazon Nova AI Challenge, team lead, $250,000 award, 2026
- UCLA Samueli Fellowship, 2025–2026
- USENIX Security: Noteworthy Artifact Reviewer (2026), Distinguished Artifact Reviewer (2025)
- Student Travel Grants, USENIX Security (2025) and NDSS (2024)
- OpenAI Researcher Access Program, OpenAI, 2024
- Student Mentee, ACM CCS, 2023
- Outstanding Undergraduate Award, Sichuan Province, 2021
Employment
- Jun – Sep 2026Applied Scientist Intern, AWS.
- Jun – Sep 2025Applied Scientist Intern, AWS.
- Jun – Sep 2023Research Assistant, The Chinese University of Hong Kong.
Services
- Program CommitteesAsiaCCS ’26, NeurIPS ’25–26; AEC for USENIX Security ’25–26, PoPETs ’25, ACM CCS ’23–24, ISSTA ’24; MSR Junior PC ’24.
- External ReviewerIEEE S&P ’24–25; USENIX Security ’24.
- Leadership & TeachingLACC Coordinator ’24; Teaching Assistant for Computer Security (UCLA ECE 117 / CS 38).