{"paper":{"title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Sheng Zhong, Tingting Wu, Wei Tong, Xin Ge, Yunlong Mao, Zirui Huang","submitted_at":"2026-08-03T12:35:51Z","abstract_excerpt":"The proliferation of customized Large Language Models (LLMs) poses critical risks of Data Intellectual Property (Data IP) infringement via unauthorized fine-tuning on proprietary data. Existing audit techniques are limited, as they require intervention during data preparation or training and remain fragile under malicious obfuscations such as data paraphrasing and knowledge distillation.\n  We propose \\textit{Distribution Provenance Audit (DPA)}, a post-hoc framework for auditing data IP infringement in LLM fine-tuning under black-box and malicious settings. DPA is grounded in a critical insigh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02154","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2608.02154/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}