Portrait of Peiran Wang

I’m Peiran Wang (王沛然 in Chinese, you can speak as “Pay-than, Wang”), a CS PhD student in UCLA. I am currently interested in general AI Security (including LLM security, privacy, etc. Especially system security for LLM recently), Machine Learning System (MLSys), usable security, fraud detection and program analysis, etc. I graduated from Sichuan University in Cybersecurity Talented Class in 2022 (18/172). During my undergraduate, I got National Scholarship (3/172), and got GPA of 3.92 (rank 2/172). I’m currently a CS PhD student in UCLA, under the supervision of Prof. Yuan Tian.

I am actively seeking Summer 2027 research internship opportunities in AI security and LLM agents. Feel free to reach out!

Nov 05, 2026 MetaPI, accepted to the NeurIPS 2026 Evaluations & Datasets Track, is now on arXiv!
Sep 01, 2026 Finished the research internship at NVIDIA Research.
Jun 01, 2026 Started my research internship at NVIDIA Research.
May 26, 2026 Three new preprints on LLM agent security are on arXiv: Options, Not Clicks, Reframing LLM Agent Security as an Agent–Human Interaction Problem, and Aligning Provenance with Authorization.
Apr 04, 2026 FineSteer is accepted to the ACL 2026 main conference, and our social deduction games paper to Findings of ACL 2026!
Feb 21, 2026 New preprint on arXiv: From Docs to Descriptions: Smell-Aware Evaluation of MCP Server Descriptions.

Research Interests

Details →

Selected Publications

Full list →
  1. NeurIPS 2026
    2026-NeurIPS-MetaPI.png
    MetaPI: Constructing Prompt Injection Benchmarks from Any Agent Benchmarks
    Peiran Wang*, Chong Xiang*, Wenjie Qu, and 4 more authors
    In 40th Conference on Neural Information Processing Systems (NeurIPS), Evaluations and Datasets Track, 2026
  2. arXiv 2026
    2026-Arxiv-PI-SoK.png
    The Landscape of Prompt Injection Threats in LLM Agents: From Taxonomy to Analysis
    Peiran Wang, Xinfeng Li, Chong Xiang, and 5 more authors
    arXiv preprint, 2026
  3. arXiv 2025
    2025-Arxiv-AgentArmor.png
    AgentArmor: Enforcing Program Analysis on Agent Runtime Trace to Defend Against Prompt Injection
    Peiran Wang, Yang Liu, Yunfei Lu, and 6 more authors
    arXiv preprint, 2025
  4. TMLR 2025
    2025-Arxiv-DS_Agent_Survey.png
    Large Language Model-based Data Science Agent: A Survey
    Ke Chen, Peiran Wang, Yaoning Yu, and 2 more authors
    Transactions on Machine Learning Research, 2025
  5. arXiv 2025
    2025-Arxiv-HaluProbe.png
    What Are Models Thinking About? Understanding Large Language Model Hallucinations "Psychology" Through Model Inner State Analysis
    Peiran Wang, Yang Liu, Yunfei Lu, and 2 more authors
    arXiv preprint, 2025
  6. CCS 2024
    2024-CCS-Moderator.png
    Moderator: Moderating Text-to-Image Diffusion Models through Fine-grained Context-based Policies
    Peiran Wang, Qiyu Li, Longxuan Yu, and 3 more authors
    In 31st ACM Conference on Computer and Communications Security (CCS), 2024
    🏆 CCS Distinguished Paper Award

Honors & Awards

  • CCS Distinguished Paper Award, ACM. 2024
  • Star of Tomorrow, Microsoft Research Asia. 2022
  • ISCC Best Paper Award, IEEE. 2021
  • National Scholarship, Ministry of Education, China. 2019
  • 1st Level Scholarship, Sichuan University. 2019

Experience

Full CV →
  • Research Intern @ NVIDIA Research Jun 2026 – Sep 2026
  • Research Assistant @ University of California, Los Angeles Sep 2025 – Present
  • Research Intern @ ByteDance Inc. Mar 2025 – Aug 2025
  • Research Intern @ ByteDance Inc. Jul 2024 – Jan 2025
  • Research Intern @ University of Wisconsin-Madison SaFoLab Aug 2024 – Mar 2025
  • Research Intern @ University of Illinois Urbana-Champaign Dream Lab Sep 2024 – Mar 2025
  • Research Intern @ Baidu Inc. May 2024 – Jul 2024
  • Research Intern @ University of California San Diego DataSmith Lab May 2023 – Feb 2024
  • Investment Intern @ Future Capital May 2023 – Aug 2023
  • Research Intern @ Microsoft Research Asia Aug 2021 – Jun 2022
  • Research Assistant @ Sichuan University Beck Lab & CodeSec Lab May 2020 – Jun 2022