log in  |  register  |  feedback?  |  help  |  web accessibility
‘Do Anything Now’: Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models
Patrick Gough
5105 Brendan Iribe Center for Computer Science and Engineering (IRB)
Tuesday, February 25, 2025, 12:30-1:30 pm
  • You are subscribed to this talk through .
  • You are watching this talk through .
  • You are subscribed to this talk. (unsubscribe, watch)
  • You are watching this talk. (unwatch, subscribe)
  • You are not subscribed to this talk. (watch, subscribe)
Abstract
At reading group tomorrow, 2/25, Patrick Gough will give a talk on "‘Do Anything Now’: Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models." Hope to see you there at 12:30pm in IRB 5105 or on Zoom! If you want lunch, please fill out this form before 9:30am tomorrow.
This talk is organized by Wentao Guo