{"data":{"id":"35f97677-276f-4037-975a-2d0996a44e13","title":"Watermarking Language Models Through Language Models","summary":"Researchers introduce a prompt-guided watermarking framework for LLM outputs that works at the input level and needs no access to model parameters or decoding logits. It uses three cooperating LMs: a prompting LM that writes watermarking instructions, a marking LM that generates watermarked outputs, and a detecting LM that classifies whether a response carries a watermark. Across 25 prompting and marking LM combinations, including GPT-4o, Mistral, LLaMA3 and DeepSeek, the signals generalize across architectures and remain robust under fine-tuning, distillation and prompt-based adversarial attacks.","solution":"N/A -- no mitigation discussed in source.","labels":["research","security"],"sourceUrl":"http://ieeexplore.ieee.org/document/11146861","publishedAt":"2025-09-02T13:20:28.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["GPT-4o","Mistral","LLaMA3","DeepSeek"],"classifierModel":"claude-haiku-5-5","classifierPromptVersion":"v4","summaryPromptVersion":"v2","headline":null,"headlinePromptVersion":null,"cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"epssCheckedAt":null,"kevDateAdded":null,"advisoryAliases":null,"affectedPackagesSource":null,"affectedPackagesCheckedAt":null,"patchAvailable":null,"disclosureDate":"2025-09-02T13:20:28.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":null,"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.9,"researchCategory":"peer_reviewed","atlasIds":null}}