{"data":{"id":"7107ff91-f16e-4925-af9e-9f9a34e82a9d","title":"Perturbation, Not Provenance: Why Activation Steering Does Not Make a Robust Text Watermark","summary":"Researchers tested whether steering LLM activations along semantic directions (formality, sentiment, complexity, and a random control) could make a robust text watermark, comparing it against the standard logit-based KGW watermark. At matched fluency (within 1.15 times the original perplexity), KGW reached an AUC of 0.81 against a sentence-level paraphraser while the best steering direction reached 0.65. A random direction was as detectable as a meaningful one, so the signal was not semantic.","solution":"N/A -- no mitigation discussed in source.","labels":["research","security"],"sourceUrl":"https://arxiv.org/abs/2610.17810v1","publishedAt":"2026-10-13T06:36:41.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":[],"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":"2026-10-13T06:36:41.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["integrity"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":null}}