{"data":{"id":"3c162234-86f7-4806-889b-4f0f3bf90bef","title":"Inner-Probe: Discovering Copyright-Related Data Generation in LLM Architecture","summary":"LLMs trained on copyrighted datasets risk generating text that infringes on copyright, and current detection methods struggle to identify which specific data sources influenced the output. Inner-Probe is a new lightweight framework that analyzes multihead attention (MHA, the mechanism LLMs use to focus on relevant parts of input when generating text) to better identify which copyrighted subdatasets contributed to generated text and to filter out noncopyrighted content, achieving significantly better accuracy and efficiency than existing approaches.","solution":"N/A -- no mitigation discussed in source.","labels":["research","security"],"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,"affectedVendors":[],"affectedVendorsRaw":[],"classifierModel":"claude-haiku-4-5-20251001","classifierPromptVersion":"v3","cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"patchAvailable":null,"disclosureDate":"2025-12-19T13:20:53.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["confidentiality"],"aiComponentTargeted":"training_data","llmSpecific":true,"classifierConfidence":0.92,"researchCategory":"peer_reviewed","atlasIds":null}}