{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5RPCP3ZZKUO4VLIHVCI3VWPYJJ","short_pith_number":"pith:5RPCP3ZZ","schema_version":"1.0","canonical_sha256":"ec5e27ef39551dcaad07a891bad9f84a6da52b1c0e096592fbfc7544cc830c5e","source":{"kind":"arxiv","id":"2404.19420","version":1},"attestation_state":"computed","paper":{"title":"Let's Focus: Focused Backdoor Attack against Federated Transfer Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Antonino Nocera, Marco Arazzi, Stefanos Koffas, Stjepan Picek","submitted_at":"2024-04-30T10:11:44Z","abstract_excerpt":"Federated Transfer Learning (FTL) is the most general variation of Federated Learning. According to this distributed paradigm, a feature learning pre-step is commonly carried out by only one party, typically the server, on publicly shared data. After that, the Federated Learning phase takes place to train a classifier collaboratively using the learned feature extractor. Each involved client contributes by locally training only the classification layers on a private training set. The peculiarity of an FTL scenario makes it hard to understand whether poisoning attacks can be developed to craft a"},"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":"2404.19420","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-30T10:11:44Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"87d7bac5b98157ca7c50024e85f400ecbc39b37a2c2aa1de3b47d0a39d455ab7","abstract_canon_sha256":"ec91955fc828157a870a9ea3c1555a7ba32dcfc6d61410922a1640c999e6e525"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:13:43.514387Z","signature_b64":"ABsng69nemEgh6iNfINGz3q0Fh4fiSvv3UsWqRrV9Pfy8qZLNaudpr/pbbZs5JeOeIsmD22LY9cRyLJ61CNwAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec5e27ef39551dcaad07a891bad9f84a6da52b1c0e096592fbfc7544cc830c5e","last_reissued_at":"2026-07-05T08:13:43.513900Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:13:43.513900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Let's Focus: Focused Backdoor Attack against Federated Transfer Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Antonino Nocera, Marco Arazzi, Stefanos Koffas, Stjepan Picek","submitted_at":"2024-04-30T10:11:44Z","abstract_excerpt":"Federated Transfer Learning (FTL) is the most general variation of Federated Learning. According to this distributed paradigm, a feature learning pre-step is commonly carried out by only one party, typically the server, on publicly shared data. After that, the Federated Learning phase takes place to train a classifier collaboratively using the learned feature extractor. Each involved client contributes by locally training only the classification layers on a private training set. The peculiarity of an FTL scenario makes it hard to understand whether poisoning attacks can be developed to craft a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.19420","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/2404.19420/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":"2404.19420","created_at":"2026-07-05T08:13:43.513948+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.19420v1","created_at":"2026-07-05T08:13:43.513948+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.19420","created_at":"2026-07-05T08:13:43.513948+00:00"},{"alias_kind":"pith_short_12","alias_value":"5RPCP3ZZKUO4","created_at":"2026-07-05T08:13:43.513948+00:00"},{"alias_kind":"pith_short_16","alias_value":"5RPCP3ZZKUO4VLIH","created_at":"2026-07-05T08:13:43.513948+00:00"},{"alias_kind":"pith_short_8","alias_value":"5RPCP3ZZ","created_at":"2026-07-05T08:13:43.513948+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.12522","citing_title":"When Forgetting Triggers Backdoors: A Clean Unlearning Attack","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5RPCP3ZZKUO4VLIHVCI3VWPYJJ","json":"https://pith.science/pith/5RPCP3ZZKUO4VLIHVCI3VWPYJJ.json","graph_json":"https://pith.science/api/pith-number/5RPCP3ZZKUO4VLIHVCI3VWPYJJ/graph.json","events_json":"https://pith.science/api/pith-number/5RPCP3ZZKUO4VLIHVCI3VWPYJJ/events.json","paper":"https://pith.science/paper/5RPCP3ZZ"},"agent_actions":{"view_html":"https://pith.science/pith/5RPCP3ZZKUO4VLIHVCI3VWPYJJ","download_json":"https://pith.science/pith/5RPCP3ZZKUO4VLIHVCI3VWPYJJ.json","view_paper":"https://pith.science/paper/5RPCP3ZZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.19420&json=true","fetch_graph":"https://pith.science/api/pith-number/5RPCP3ZZKUO4VLIHVCI3VWPYJJ/graph.json","fetch_events":"https://pith.science/api/pith-number/5RPCP3ZZKUO4VLIHVCI3VWPYJJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5RPCP3ZZKUO4VLIHVCI3VWPYJJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5RPCP3ZZKUO4VLIHVCI3VWPYJJ/action/storage_attestation","attest_author":"https://pith.science/pith/5RPCP3ZZKUO4VLIHVCI3VWPYJJ/action/author_attestation","sign_citation":"https://pith.science/pith/5RPCP3ZZKUO4VLIHVCI3VWPYJJ/action/citation_signature","submit_replication":"https://pith.science/pith/5RPCP3ZZKUO4VLIHVCI3VWPYJJ/action/replication_record"}},"created_at":"2026-07-05T08:13:43.513948+00:00","updated_at":"2026-07-05T08:13:43.513948+00:00"}