What’s new?

  • (2024.11) My popular-science novel “When Trojan Virus Meets Military Training” won the Outstanding Popular Science Work Award from China Science Writers Association! May it inspire love for cybersecurity in young readers ;D
  • (2024.09) Our paper titled “The Death and Life of Great Prompts: Analyzing the Evolution of LLM Prompts from the Structural Perspective” got accepted in EMNLP 2024!
  • (2024.09) Our paper titled “ModScan: Measuring Stereotypical Bias in Large Vision-Language Models from Vision and Language Modalities” got accepted in EMNLP 2024!
  • (2024.07) I will serve on the Program Committee of USENIX Security 2025!
  • (2024.07) I will serve on the Program Committee of SaTML 2025!
  • (2024.06) I will serve on the Poster Program Committee of USENIX Security 2024.
  • (2024.06) I received the Abbe Grant from the Carl-Zeiss-Stiftung Foundation and am honored to be selected as a Young Researcher to attend the 11th Heidelberg Laureate Forum!
  • (2024.05) We released a technical report “Voice Jailbreak Attacks Against GPT-4o” on how to jailbreak GPT-4o with voice!
  • (2024.05) Our paper titled “MGTBench: Benchmarking Machine-Generated Text Detection” got accepted in CCS 2024!
  • (2024.05) I will serve on the Program Committee of AISec 2024!
  • (2024.04) I will serve as an AEC member of CCS 2024.
  • (2024.04) Our paper titled “Do Anything Now”: Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models” got accepted in CCS 2024! See you in Salt Lake City!
  • (2024.04) I will serve on the Poster Program Committee of IEEE S&P 2024.
  • (2024.03) Our paper titled “Games and Beyond: Analyzing the Bullet Chats of Esports Livestreaming” got accepted in ICWSM 2024! (Lux: “Lighting the way!”)
  • (2024.03) I will serve on the Program Committee of ICWSM 2024!
  • (2024.02) Our paper titled “Prompt Stealing Attacks Against Text-to-Image Generation Models” got accepted in USENIX 2024! See you in Philadelphia!
  • (2023.09) Our research on Jailbreak Prompts got covered by New Scientist and Deutschlandfunk Nova!
  • (2023.05) Our paper titled “Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models” got accepted in CCS 2023! See you in Copenhagen!