Rep2Text Recovers Private Prompts From a Single AI Hidden Vector
A new framework called Rep2Text shows that a single hidden vector inside an LLM leaks about half the words of its input, raising privacy and interpretability questions.
Source
AlphaSignal
Published
Author
AlphaSignal Newsroom
Read
1 min read
A new framework called Rep2Text shows that a single hidden vector inside an LLM leaks about half the words of its input, raising privacy and interpretability questions.
Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.
