Controlled Decoding Attacks on Black-Box LLMs
A text-only controlled-decoding method jailbreaks black-box LLMs by reconstructing and steering token distributions at a few positions.
Stories per day · 30 days
2 RSS
2 stories, newest first · one card per story
Stories tagged #controlled-decoding
Controlled Decoding Attacks on Black-Box LLMs
Researchers propose a text-only black-box LLM jailbreak that reconstructs and selectively steers token distributions.