Mind the Inconspicuous: Revealing the Hidden Weakness in Aligned LLMs' Refusal Boundaries

Name: Mind the Inconspicuous: Revealing the Hidden Weakness in Aligned LLMs' Refusal Boundaries
Duration: 15 min
Description: Talk from 34th USENIX Security Symposium (USENIX Security '25).

Jiahao Yu

34th USENIX Security Symposium (USENIX Security '25) · Day 1 · LLM Security and Attacks