{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4BOK2OSUIPEL4RDCO6FKDTIQOX","short_pith_number":"pith:4BOK2OSU","schema_version":"1.0","canonical_sha256":"e05cad3a5443c8be4462778aa1cd1075f67fb17d2cfbb73d7b052a0c347563a2","source":{"kind":"arxiv","id":"2307.03197","version":1},"attestation_state":"computed","paper":{"title":"Analyzing the vulnerabilities in SplitFed Learning: Assessing the robustness against Data Poisoning Attacks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aysha Thahsin Zahir Ismail, Raj Mani Shukla","submitted_at":"2023-07-04T00:37:12Z","abstract_excerpt":"Distributed Collaborative Machine Learning (DCML) is a potential alternative to address the privacy concerns associated with centralized machine learning. The Split learning (SL) and Federated Learning (FL) are the two effective learning approaches in DCML. Recently there have been an increased interest on the hybrid of FL and SL known as the SplitFed Learning (SFL). This research is the earliest attempt to study, analyze and present the impact of data poisoning attacks in SFL. We propose three kinds of novel attack strategies namely untargeted, targeted and distance-based attacks for SFL. All"},"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":"2307.03197","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-04T00:37:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c869d05c00daa875f2d7eabe2397d3f08d56e65ece25b8f16440b2a381654e50","abstract_canon_sha256":"7821849157c55c255484ebef9cc30e81d5d4104acd19a0c846772fabd33b4319"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:28:38.988743Z","signature_b64":"8VPLD83Lb3putfVQV9Hrp2LNAA/ew2nFPIvHlBBn3T5J/O/N3j/1vskwJ2yj0UNAPaviTF6d2seQg2TH42gBDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e05cad3a5443c8be4462778aa1cd1075f67fb17d2cfbb73d7b052a0c347563a2","last_reissued_at":"2026-07-05T06:28:38.988322Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:28:38.988322Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Analyzing the vulnerabilities in SplitFed Learning: Assessing the robustness against Data Poisoning Attacks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aysha Thahsin Zahir Ismail, Raj Mani Shukla","submitted_at":"2023-07-04T00:37:12Z","abstract_excerpt":"Distributed Collaborative Machine Learning (DCML) is a potential alternative to address the privacy concerns associated with centralized machine learning. The Split learning (SL) and Federated Learning (FL) are the two effective learning approaches in DCML. Recently there have been an increased interest on the hybrid of FL and SL known as the SplitFed Learning (SFL). This research is the earliest attempt to study, analyze and present the impact of data poisoning attacks in SFL. We propose three kinds of novel attack strategies namely untargeted, targeted and distance-based attacks for SFL. All"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.03197","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/2307.03197/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":"2307.03197","created_at":"2026-07-05T06:28:38.988385+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.03197v1","created_at":"2026-07-05T06:28:38.988385+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.03197","created_at":"2026-07-05T06:28:38.988385+00:00"},{"alias_kind":"pith_short_12","alias_value":"4BOK2OSUIPEL","created_at":"2026-07-05T06:28:38.988385+00:00"},{"alias_kind":"pith_short_16","alias_value":"4BOK2OSUIPEL4RDC","created_at":"2026-07-05T06:28:38.988385+00:00"},{"alias_kind":"pith_short_8","alias_value":"4BOK2OSU","created_at":"2026-07-05T06:28:38.988385+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.05872","citing_title":"A Taxonomy of Attacks and Defenses in Split Learning","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4BOK2OSUIPEL4RDCO6FKDTIQOX","json":"https://pith.science/pith/4BOK2OSUIPEL4RDCO6FKDTIQOX.json","graph_json":"https://pith.science/api/pith-number/4BOK2OSUIPEL4RDCO6FKDTIQOX/graph.json","events_json":"https://pith.science/api/pith-number/4BOK2OSUIPEL4RDCO6FKDTIQOX/events.json","paper":"https://pith.science/paper/4BOK2OSU"},"agent_actions":{"view_html":"https://pith.science/pith/4BOK2OSUIPEL4RDCO6FKDTIQOX","download_json":"https://pith.science/pith/4BOK2OSUIPEL4RDCO6FKDTIQOX.json","view_paper":"https://pith.science/paper/4BOK2OSU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.03197&json=true","fetch_graph":"https://pith.science/api/pith-number/4BOK2OSUIPEL4RDCO6FKDTIQOX/graph.json","fetch_events":"https://pith.science/api/pith-number/4BOK2OSUIPEL4RDCO6FKDTIQOX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4BOK2OSUIPEL4RDCO6FKDTIQOX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4BOK2OSUIPEL4RDCO6FKDTIQOX/action/storage_attestation","attest_author":"https://pith.science/pith/4BOK2OSUIPEL4RDCO6FKDTIQOX/action/author_attestation","sign_citation":"https://pith.science/pith/4BOK2OSUIPEL4RDCO6FKDTIQOX/action/citation_signature","submit_replication":"https://pith.science/pith/4BOK2OSUIPEL4RDCO6FKDTIQOX/action/replication_record"}},"created_at":"2026-07-05T06:28:38.988385+00:00","updated_at":"2026-07-05T06:28:38.988385+00:00"}