Generative AI

(USENIX Security 2024) This is a systematic study on jailbreak attacks against commercial large language model (LLM) systems. We analyzed existing jailbreak prompts, examined their contributing factors, and conducted user studies to explore human behavioral patterns during jailbreak attempts.

(CCS 2023) We introduced the concept of proactive defense to combat unauthorized speech synthesis. Our defense works by adding perturbations to speech samples before releasing them into the public domain (e.g., social media and streaming platforms). While the processed sample still sounds like the victim to humans, when it is used for speech synthesis by the attacker, the resulting synthetic speech would resemble others’ voices rather than the victim’s.