Yixin Wu

profile2.jpeg

Guangzhou, China

I’m an incoming assistant professor in the AI Thrust, Information Hub of HKUST(GZ). I received my Ph.D. from CISPA Helmholtz Center for Information Security, where I was fortunate to be advised by Prof. Michael Backes and Dr. Yang Zhang. Before joining CISPA, I received my Bachelor’s degree from Sichuan University, where I worked with Prof. Cheng Huang.

My research focuses on the security, privacy, and transparency of AI systems and the use of AI agents for security and privacy tasks. I develop algorithms, build autonomous agents, and conduct large-scale empirical analyses to study emerging attacks and defenses, audit AI systems, measure real-world AI use and misuse, and understand social behavior through agent-based simulation.

Join Us

I am looking for self-motivated students to join my group at HKUST(GZ).

  • RAs: Immediate openings; current HKUST(GZ) students are also welcome.
  • Ph.D. Students: 3 openings for Spring/Fall 2027.

Please drop me an email (yixinwu@hkust-gz.edu.cn) if you are interested in working with me!


Research Interests

AI Security, Privacy, and Transparency

Studying attacks, defenses, and trustworthy mechanisms for foundation models and agentic AI systems.

AI Agents for Security and Privacy

Building autonomous agents to discover, assess, and mitigate security and privacy risks in real-world systems.

AI Measurement and Simulation

Measuring real-world AI use and misuse at scale, and using agent-based simulation to understand social behavior and emerging risks.


Honors and Awards

  • 2025
    Rising Star in EECS 2025, MIT
  • 2025
    ML and Systems Rising Star, MLCommons
  • 2025
    Abbe Grant, Carl-Zeiss-Stiftung
  • 2025
    Heidelberg Laureate Forum Young Researcher, The 12th Heidelberg Laureate Forum

News

Aug 2026 I will join the AI Thrust, Information Hub of HKUST(GZ) as an assistant professor. I am recruiting RAs and Ph.D. students. Please contact me if you are interested in working with me!
Jun 2026 Our paper titled “GEO-Detective: Unveiling Location Privacy Risks in Images with LLM Agents” was accepted by ECCV 2026.
Apr 2026 Our paper titled “InferPilot: Autonomous Inference Attacks Against ML Services With LLM-Based Agents” was accepted by ACL Findings 2026.
Apr 2026 Our paper titled “Peering Behind the Shield: Guardrail Identification in Large Language Models” was accepted by ACL Findings 2026.
Apr 2026 Our paper titled “Rethinking Assessments of Prompt Injection Attacks” was accepted by ACL Findings 2026.
Sep 2025 I was selected as a Rising Star in EECS 2025!
Jul 2025 Our paper titled “UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Images” was accepted by ACM CCS 2025. See the website for more details!
Jun 2025 I was selected to recieve the Abbe Grant from the Carl-Zeiss-Stiftung!
May 2025 I was selected as a Heidelberg Laureate Forum Young Researcher!
Mar 2025 I was selected as a ML and Systems Rising Star!

Selected Publications

  1. ACL Findings
    InferPilot: Autonomous Inference Attacks Against ML Services With LLM-Based Agents
    Yixin Wu, Rui Wen, Chi Cui, Michael Backes, and Yang Zhang
    In Annual Meeting of the Association for Computational Linguistics (ACL), 2026
  2. Usenix Security
    Yixin Wu, Ziqing Yang, Yun Shen, Michael Backes, and Yang Zhang
    In USENIX Security Symposium (USENIX Security), 2025
  3. Usenix Security
    Yixin Wu, Ning Yu, Michael Backes, Yun Shen, and Yang Zhang
    In USENIX Security Symposium (USENIX Security), 2025
  4. Usenix Security
    Yixin Wu, Rui Wen, Michael Backes, Pascal Berrang, Mathias Humbert, Yun Shen, and Yang Zhang
    In USENIX Security Symposium (USENIX Security), 2024
  5. CCS
    Yixin Wu, Yun Shen, Michael Backes, and Yang Zhang
    In ACM Conference on Computer and Communications Security (CCS), 2024
  6. PETS
    Yixin Wu, Xinlei He, Pascal Berrang, Mathias Humbert, Michael Backes, Neil Zhenqiang Gong, and Yang Zhang
    In Privacy Enhancing Technologies Symposium (PETS), 2024