{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UQIZ2Z6SGVALNWAIS7ZAL6OSFA","short_pith_number":"pith:UQIZ2Z6S","schema_version":"1.0","canonical_sha256":"a4119d67d23540b6d80897f205f9d2283eb5029a389207875c9f5def89d362fa","source":{"kind":"arxiv","id":"2412.17740","version":1},"attestation_state":"computed","paper":{"title":"Sensitivity Curve Maximization: Attacking Robust Aggregators in Distributed Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.SP"],"primary_cat":"cs.LG","authors_text":"Abdelhak M. Zoubir, Christian A. Schroth, Stefan Vlaski","submitted_at":"2024-12-23T17:44:03Z","abstract_excerpt":"In distributed learning agents aim at collaboratively solving a global learning problem. It becomes more and more likely that individual agents are malicious or faulty with an increasing size of the network. This leads to a degeneration or complete breakdown of the learning process. Classical aggregation schemes are prone to breakdown at small contamination rates, therefore robust aggregation schemes are sought for. While robust aggregation schemes can generally tolerate larger contamination rates, many have been shown to be susceptible to carefully crafted malicious attacks. In this work, we "},"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":"2412.17740","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-23T17:44:03Z","cross_cats_sorted":["eess.SP"],"title_canon_sha256":"5bfdbb4620da65bd92834e8da6bf91968739b12b8e651850a98d9dc75241159e","abstract_canon_sha256":"2f75911f4967a21f6412df953c9710e196fc118750dd655d21b5a3f212ace32b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:26.826959Z","signature_b64":"m4HWTSSFbtKpot/wt5JhtrLl9pVRq2bGt/NOqHk2ZpfQVUOECB8N58spom7qi1C30LzvC7f8QT0mt+vmXhUXCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4119d67d23540b6d80897f205f9d2283eb5029a389207875c9f5def89d362fa","last_reissued_at":"2026-07-05T09:53:26.826534Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:26.826534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sensitivity Curve Maximization: Attacking Robust Aggregators in Distributed Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.SP"],"primary_cat":"cs.LG","authors_text":"Abdelhak M. Zoubir, Christian A. Schroth, Stefan Vlaski","submitted_at":"2024-12-23T17:44:03Z","abstract_excerpt":"In distributed learning agents aim at collaboratively solving a global learning problem. It becomes more and more likely that individual agents are malicious or faulty with an increasing size of the network. This leads to a degeneration or complete breakdown of the learning process. Classical aggregation schemes are prone to breakdown at small contamination rates, therefore robust aggregation schemes are sought for. While robust aggregation schemes can generally tolerate larger contamination rates, many have been shown to be susceptible to carefully crafted malicious attacks. In this work, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17740","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/2412.17740/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":"2412.17740","created_at":"2026-07-05T09:53:26.826585+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.17740v1","created_at":"2026-07-05T09:53:26.826585+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17740","created_at":"2026-07-05T09:53:26.826585+00:00"},{"alias_kind":"pith_short_12","alias_value":"UQIZ2Z6SGVAL","created_at":"2026-07-05T09:53:26.826585+00:00"},{"alias_kind":"pith_short_16","alias_value":"UQIZ2Z6SGVALNWAI","created_at":"2026-07-05T09:53:26.826585+00:00"},{"alias_kind":"pith_short_8","alias_value":"UQIZ2Z6S","created_at":"2026-07-05T09:53:26.826585+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.09438","citing_title":"Generalization Error Analysis for Attack-Free and Byzantine-Resilient Decentralized Learning with Data Heterogeneity","ref_index":52,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UQIZ2Z6SGVALNWAIS7ZAL6OSFA","json":"https://pith.science/pith/UQIZ2Z6SGVALNWAIS7ZAL6OSFA.json","graph_json":"https://pith.science/api/pith-number/UQIZ2Z6SGVALNWAIS7ZAL6OSFA/graph.json","events_json":"https://pith.science/api/pith-number/UQIZ2Z6SGVALNWAIS7ZAL6OSFA/events.json","paper":"https://pith.science/paper/UQIZ2Z6S"},"agent_actions":{"view_html":"https://pith.science/pith/UQIZ2Z6SGVALNWAIS7ZAL6OSFA","download_json":"https://pith.science/pith/UQIZ2Z6SGVALNWAIS7ZAL6OSFA.json","view_paper":"https://pith.science/paper/UQIZ2Z6S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.17740&json=true","fetch_graph":"https://pith.science/api/pith-number/UQIZ2Z6SGVALNWAIS7ZAL6OSFA/graph.json","fetch_events":"https://pith.science/api/pith-number/UQIZ2Z6SGVALNWAIS7ZAL6OSFA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UQIZ2Z6SGVALNWAIS7ZAL6OSFA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UQIZ2Z6SGVALNWAIS7ZAL6OSFA/action/storage_attestation","attest_author":"https://pith.science/pith/UQIZ2Z6SGVALNWAIS7ZAL6OSFA/action/author_attestation","sign_citation":"https://pith.science/pith/UQIZ2Z6SGVALNWAIS7ZAL6OSFA/action/citation_signature","submit_replication":"https://pith.science/pith/UQIZ2Z6SGVALNWAIS7ZAL6OSFA/action/replication_record"}},"created_at":"2026-07-05T09:53:26.826585+00:00","updated_at":"2026-07-05T09:53:26.826585+00:00"}