Diffusion Language Models for Perplexity-Aware Black-Box Attacks
\emph{Continuous-space} attacks find prompts that trigger malicious behaviors, such as overthinking, in black-box LLMs by sampling or optimizing over a low-dimensional Gaussian latent space and decoding it to text through a \emph{random mapping} and nearest-token lookup.
By Ali Al-Lawati, Elsayed Eshra, Dongwon Lee, Suhang WangarXiv - stat.ML
Read the full story
Originally published by arXiv - stat.ML on Oct 23, 2026.
Comments
Sign in to join the discussion.