Ali Al-Lawati, Elsayed Eshra, Dongwon Lee, Suhang Wang · 2026 · arXiv
DOI: 10.48550/arXiv.2610.31558 · open-access PDF
\emph{Continuous-space} 공격은 블랙박스 LLM에서 샘플링 또는 낮은 차원 Gaussian 라틴 스페이스를 통해 최적화하고 텍스트로 디코딩하여 \emph{random mapping} 및 가장 가까운 토큰 검색을 통해 악의적 인 행동을 유발합니다. overthinking과 같은 샘플링은 언어에서 배우지 않기 때문에, 그것의 샘플링은 매우 자연스럽지 않을 수 있으며, 그러한 가드레이를 통해 쉽게 감지 할 수 있으며, 그들이 제공하는 위험 추정은 자연스러운 샘플링에 근거하지 않습니다.
Machine translation (Meta M2M100); the English original follows.
\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. Because the random mapping is not learned from language, its prompts can be highly unnatural, and as such easily detectable through input guardrails, and the risk estimates they yield are not grounded in natural prompts. In this paper, we demonstrate that the same continuous latent-space framework can be coupled directly to a
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.31558, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange