Invited Talks

  • Max Planck Institute for Security and Privacy (MPI-SP)
    Understanding and Mitigating LLM Misuse in the Real World
    Bochum, Germany, July 2025
  • Wuhan University
    When LLMs Are in the Wrong Hands
    Virtual, July 2025
  • France National Commission on Informatics and Liberty (CNIL) Privacy Research Day
    HateBench: Benchmarking Hate Speech Detectors on LLM-Generated Content and Hate Campaigns
    Paris, France, July 2025
  • LLMApp Workshop @FSE 2025
    GPTracker: A Large-Scale Measurement of Misuse and Knowledge File Leakage in GPTs
    Trondheim, Norway, June 2025
  • Leiden University
    When LLMs Are in the Wrong Hands
    Leiden, Netherlands, June 2025
  • Delft University of Technology (TU Delft)
    When LLMs Are in the Wrong Hands
    Delft, Netherlands, June 2025
  • MLCommons ML and Systems Rising Stars Workshop
    “Do Anything Now”: Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models
    San Francisco, USA, May 2025
  • King Abdullah University of Science and Technology (KAUST)
    Understand and Mitigate AI System Misuse in the Real World
    Thuwal, Saudi Arabia, April 2025
  • Hong Kong University of Science and Technology (Guangzhou)
    Emerging Attacks in the Era of Generative AI (Guest Lecture)
    Virtual, December 2024
  • Heidelberg Laureate Forum (HLF)
    “Do Anything Now”: Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models
    Heidelberg, Germany, October 2024
  • The Ohio State University
    Emerging Attacks in the Era of Generative AI
    Virtual, September 2024
  • AEGIS Symposium on Cyber Security
    Emerging Attacks in the Era of Generative AI
    Virtual, June 2024
  • Google
    Emerging Attacks in the Era of Generative AI
    Virtual, April 2024
  • Shanghai Jiao Tong University
    Understanding and Quantifying the Safety Issues of Large Foundation Models
    Shanghai, China, October 2023
  • Fudan University
    Understanding and Quantifying the Safety Issues of Large Foundation Models
    Shanghai, China, October 2023
  • Sichuan University
    Understanding and Quantifying the Safety Issues of Large Foundation Models
    Chengdu, China, September 2023
  • University of Electronic Science and Technology of China
    Understanding and Quantifying the Safety Issues of Large Foundation Models
    Chengdu, China, September 2023
  • AEGIS Symposium on Cyber Security
    Measuring the Reliability of ChatGPT
    Virtual, June 2023
  • Hack In The Box Conference (HITBConf)
    Solving The Last Mile Problem Between Machine Learning and Security Operations
    Beijing, China, October 2018
    [pdf]  [link]