{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZCTRY2YXPGO6YINFCU7AH65DK4","short_pith_number":"pith:ZCTRY2YX","schema_version":"1.0","canonical_sha256":"c8a71c6b17799dec21a5153e03fba357109d8dea2fde5a4aed8cf189ad174a4f","source":{"kind":"arxiv","id":"2509.08995","version":1},"attestation_state":"computed","paper":{"title":"When FinTech Meets Privacy: Securing Financial LLMs with Differential Private Fine-Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Honghui Xu, Hoyeung Leung, Jia Wei, Sichen Zhu, Xiaoyi Wang","submitted_at":"2025-09-10T20:43:08Z","abstract_excerpt":"The integration of Large Language Models (LLMs) into financial technology (FinTech) has revolutionized the analysis and processing of complex financial data, driving advancements in real-time decision-making and analytics. With the growing trend of deploying AI models on edge devices for financial applications, ensuring the privacy of sensitive financial data has become a significant challenge. To address this, we propose DPFinLLM, a privacy-enhanced, lightweight LLM specifically designed for on-device financial applications. DPFinLLM combines a robust differential privacy mechanism with a str"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2509.08995","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-09-10T20:43:08Z","cross_cats_sorted":[],"title_canon_sha256":"6c505b00d27539b17452d8bbc2afbe3e6619bae852f7ec0a32ac2874d007a3fe","abstract_canon_sha256":"d8ce406b3b134074825a78fef53bc27d9789a0937c1f60ddc727d3e3f5f224b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:27.130410Z","signature_b64":"lpoz1gYgdfF1PqFwOspsDeDMutO/ZGVyMWVJBhydz+TOEMjoST6fVyu3GUEHDm72dWJ+SDi00T1uS4jJH3eWDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8a71c6b17799dec21a5153e03fba357109d8dea2fde5a4aed8cf189ad174a4f","last_reissued_at":"2026-07-05T12:09:27.129858Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:27.129858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When FinTech Meets Privacy: Securing Financial LLMs with Differential Private Fine-Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Honghui Xu, Hoyeung Leung, Jia Wei, Sichen Zhu, Xiaoyi Wang","submitted_at":"2025-09-10T20:43:08Z","abstract_excerpt":"The integration of Large Language Models (LLMs) into financial technology (FinTech) has revolutionized the analysis and processing of complex financial data, driving advancements in real-time decision-making and analytics. With the growing trend of deploying AI models on edge devices for financial applications, ensuring the privacy of sensitive financial data has become a significant challenge. To address this, we propose DPFinLLM, a privacy-enhanced, lightweight LLM specifically designed for on-device financial applications. DPFinLLM combines a robust differential privacy mechanism with a str"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.08995","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/2509.08995/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2509.08995","created_at":"2026-07-05T12:09:27.129947+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.08995v1","created_at":"2026-07-05T12:09:27.129947+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.08995","created_at":"2026-07-05T12:09:27.129947+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZCTRY2YXPGO6","created_at":"2026-07-05T12:09:27.129947+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZCTRY2YXPGO6YINF","created_at":"2026-07-05T12:09:27.129947+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZCTRY2YX","created_at":"2026-07-05T12:09:27.129947+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29450","citing_title":"Protecting On-Device AI Inference: A Systematic Review of Attacks and Defence Mechanisms","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZCTRY2YXPGO6YINFCU7AH65DK4","json":"https://pith.science/pith/ZCTRY2YXPGO6YINFCU7AH65DK4.json","graph_json":"https://pith.science/api/pith-number/ZCTRY2YXPGO6YINFCU7AH65DK4/graph.json","events_json":"https://pith.science/api/pith-number/ZCTRY2YXPGO6YINFCU7AH65DK4/events.json","paper":"https://pith.science/paper/ZCTRY2YX"},"agent_actions":{"view_html":"https://pith.science/pith/ZCTRY2YXPGO6YINFCU7AH65DK4","download_json":"https://pith.science/pith/ZCTRY2YXPGO6YINFCU7AH65DK4.json","view_paper":"https://pith.science/paper/ZCTRY2YX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.08995&json=true","fetch_graph":"https://pith.science/api/pith-number/ZCTRY2YXPGO6YINFCU7AH65DK4/graph.json","fetch_events":"https://pith.science/api/pith-number/ZCTRY2YXPGO6YINFCU7AH65DK4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZCTRY2YXPGO6YINFCU7AH65DK4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZCTRY2YXPGO6YINFCU7AH65DK4/action/storage_attestation","attest_author":"https://pith.science/pith/ZCTRY2YXPGO6YINFCU7AH65DK4/action/author_attestation","sign_citation":"https://pith.science/pith/ZCTRY2YXPGO6YINFCU7AH65DK4/action/citation_signature","submit_replication":"https://pith.science/pith/ZCTRY2YXPGO6YINFCU7AH65DK4/action/replication_record"}},"created_at":"2026-07-05T12:09:27.129947+00:00","updated_at":"2026-07-05T12:09:27.129947+00:00"}