Chaowei Xiao
21 papers · 1851 citations
Most-cited papers
- Autodan: Generating Stealthy Jailbreak Prompts On Aligned Large Language Models2023 · 698 citations
- Jailbreakv: A Benchmark For Assessing The Robustness Of Multimodal Large Language Models Against Jailbreak Attacks2024 · 215 citations
- Automatic And Universal Prompt Injection Attacks Against Large Language Models2024 · 135 citations
- Don't Listen To Me: Understanding And Exploring Jailbreak Prompts Of Large Language Models2024 · 101 citations
Topics