Ali Al-Lawati, Elsayed Eshra, Dongwon Lee, Suhang Wang · 2026 · arXiv
DOI: 10.48550/arXiv.2610.31558 · open-access PDF
\emph{continuous-space} हमलों में, ब्लैक-बॉक्स एलएलएम में बुरी तरह के व्यवहार को उजागर करने वाले प्रॉम्प्ट मिलते हैं, उदाहरण के लिए, नमूना या कम आयाम गैसियन लैटिन स्पेस पर अनुकूलन करके और इसे एक \emph{random mapping} और निकटतम टोकन खोज के माध्यम से पाठ में डिकोडिंग करके।
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