{"data":{"id":"e1b064a7-6a5a-4c11-8fcd-aaf99d152308","title":"Watermark Evidence under Open-Weight LLM Modification: Exact Bounds for Low-Rank Output Watermarks","summary":"This paper studies how modifying open-weight language models changes the evidence available to an OpenStamp-style watermark verifier. The authors derive exact bounds on expected log-likelihood-ratio evidence under a residual-span constraint, plus a high-confidence bound on miss probability for sequence-level detection. In experiments on Llama-2-7B and Mistral-7B-v0.3, INT8 quantization and 30% pruning kept test true-positive rates at 85.6-94.8%, while 500-step LoRA fine-tuning reduced them to 28.8% and 11.6%.","solution":"N/A -- no mitigation discussed in source.","labels":["research","security"],"sourceUrl":"https://arxiv.org/abs/2611.21702v1","publishedAt":"2026-11-16T15:52:38.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["model_evasion"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["Llama-2-7B","Mistral-7B-v0.3","OpenStamp"],"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":"2026-11-16T15:52:38.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["integrity"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.93,"researchCategory":"preprint","atlasIds":null}}