{"data":{"id":"3c162234-86f7-4806-889b-4f0f3bf90bef","title":"Inner-Probe: Discovering Copyright-Related Data Generation in LLM Architecture","summary":"Researchers propose Inner-Probe, a lightweight framework that estimates how much copyrighted subdatasets influence LLM-generated text. Instead of relying only on text, it trains an LSTM-based network on multihead attention (MHA) results during output generation to analyze subdataset contributions. It also detects noncopyrighted text via a concatenated global projector trained with unsupervised contrastive learning. Reported results include 3× efficiency over semantic model training on Books3, 15.04%–58.7% higher accuracy than baselines on the Pile, and a 0.104 AUC increase for noncopyrighted data filtering.","solution":"N/A -- no mitigation discussed in source.","labels":["research","privacy"],"sourceUrl":"http://ieeexplore.ieee.org/document/11306340","publishedAt":"2025-12-19T13:20:53.000Z","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":"2025-12-19T13:20:53.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":null,"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.85,"researchCategory":"peer_reviewed","atlasIds":null}}