{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZAO6OFDM4DYOHJFD7VG7BD3CK5","short_pith_number":"pith:ZAO6OFDM","schema_version":"1.0","canonical_sha256":"c81de7146ce0f0e3a4a3fd4df08f6257654c09d088fc05bf282631da5e98998a","source":{"kind":"arxiv","id":"2505.22447","version":1},"attestation_state":"computed","paper":{"title":"Privacy-preserving Prompt Personalization in Federated Learning for Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Baturalp Buyukates, Sizai Hou, Songze Li","submitted_at":"2025-05-28T15:09:56Z","abstract_excerpt":"Prompt learning is a crucial technique for adapting pre-trained multimodal language models (MLLMs) to user tasks. Federated prompt personalization (FPP) is further developed to address data heterogeneity and local overfitting, however, it exposes personalized prompts - valuable intellectual assets - to privacy risks like prompt stealing or membership inference attacks. Widely-adopted techniques like differential privacy add noise to prompts, whereas degrading personalization performance. We propose SecFPP, a secure FPP protocol harmonizing generalization, personalization, and privacy guarantee"},"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":"2505.22447","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CR","submitted_at":"2025-05-28T15:09:56Z","cross_cats_sorted":[],"title_canon_sha256":"694b1d6a947252aab23c53fdeff1904d8990d96d5c9c212896022f02e2bd76ea","abstract_canon_sha256":"efdc5c13555e3f208e0f7f84bc363d5460597161309ce254518ced80f32d9eeb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:24.209396Z","signature_b64":"IIrqRYA+aaMuzI4UY64IGnXyofNXMQOIZcPNA32SzzsWAHfsGTF/qNLl1jCf8qtxasyegfihTRoPLx3uvwBCCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c81de7146ce0f0e3a4a3fd4df08f6257654c09d088fc05bf282631da5e98998a","last_reissued_at":"2026-07-05T11:11:24.208861Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:24.208861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Privacy-preserving Prompt Personalization in Federated Learning for Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Baturalp Buyukates, Sizai Hou, Songze Li","submitted_at":"2025-05-28T15:09:56Z","abstract_excerpt":"Prompt learning is a crucial technique for adapting pre-trained multimodal language models (MLLMs) to user tasks. Federated prompt personalization (FPP) is further developed to address data heterogeneity and local overfitting, however, it exposes personalized prompts - valuable intellectual assets - to privacy risks like prompt stealing or membership inference attacks. Widely-adopted techniques like differential privacy add noise to prompts, whereas degrading personalization performance. We propose SecFPP, a secure FPP protocol harmonizing generalization, personalization, and privacy guarantee"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22447","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/2505.22447/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":"2505.22447","created_at":"2026-07-05T11:11:24.208915+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.22447v1","created_at":"2026-07-05T11:11:24.208915+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22447","created_at":"2026-07-05T11:11:24.208915+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZAO6OFDM4DYO","created_at":"2026-07-05T11:11:24.208915+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZAO6OFDM4DYOHJFD","created_at":"2026-07-05T11:11:24.208915+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZAO6OFDM","created_at":"2026-07-05T11:11:24.208915+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZAO6OFDM4DYOHJFD7VG7BD3CK5","json":"https://pith.science/pith/ZAO6OFDM4DYOHJFD7VG7BD3CK5.json","graph_json":"https://pith.science/api/pith-number/ZAO6OFDM4DYOHJFD7VG7BD3CK5/graph.json","events_json":"https://pith.science/api/pith-number/ZAO6OFDM4DYOHJFD7VG7BD3CK5/events.json","paper":"https://pith.science/paper/ZAO6OFDM"},"agent_actions":{"view_html":"https://pith.science/pith/ZAO6OFDM4DYOHJFD7VG7BD3CK5","download_json":"https://pith.science/pith/ZAO6OFDM4DYOHJFD7VG7BD3CK5.json","view_paper":"https://pith.science/paper/ZAO6OFDM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.22447&json=true","fetch_graph":"https://pith.science/api/pith-number/ZAO6OFDM4DYOHJFD7VG7BD3CK5/graph.json","fetch_events":"https://pith.science/api/pith-number/ZAO6OFDM4DYOHJFD7VG7BD3CK5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZAO6OFDM4DYOHJFD7VG7BD3CK5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZAO6OFDM4DYOHJFD7VG7BD3CK5/action/storage_attestation","attest_author":"https://pith.science/pith/ZAO6OFDM4DYOHJFD7VG7BD3CK5/action/author_attestation","sign_citation":"https://pith.science/pith/ZAO6OFDM4DYOHJFD7VG7BD3CK5/action/citation_signature","submit_replication":"https://pith.science/pith/ZAO6OFDM4DYOHJFD7VG7BD3CK5/action/replication_record"}},"created_at":"2026-07-05T11:11:24.208915+00:00","updated_at":"2026-07-05T11:11:24.208915+00:00"}