{"data":{"id":"e26cbd32-1e98-4018-9f4d-27aef322a399","title":"Watermark Basins: Black-Box Detection of Distilled LLMs","summary":"Watermark Basin Alignment (WM-Basin) is a black-box detector that identifies models distilled from a watermarked teacher without access to weights or logits. It projects generated text into gradient space and tests for alignment with a key-specific watermark basin orthogonal to ordinary fine-tuning directions. At a 0.1% false-positive rate it detects 79% of distilled models at n-gram=1 and 45% at n-gram=3, versus 29% and 1.3% for the token-level baseline, and the signal survives quantization, pruning and reinforcement-learning post-training.","solution":"N/A -- no mitigation discussed in source.","labels":["research","security"],"sourceUrl":"https://arxiv.org/abs/2610.37266v1","publishedAt":"2026-10-27T13:59:34.000Z","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":"2026-10-27T13:59:34.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":null}}