{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:IXLUB3N4XGQMZKPEX3SLOACJVC","short_pith_number":"pith:IXLUB3N4","schema_version":"1.0","canonical_sha256":"45d740edbcb9a0cca9e4bee4b70049a8b6243ba31ab1bccd0327b6309e857a43","source":{"kind":"arxiv","id":"1711.03707","version":4},"attestation_state":"computed","paper":{"title":"Learning under $p$-Tampering Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Dimitrios I. Diochnos, Mohammad Mahmoody, Saeed Mahloujifar","submitted_at":"2017-11-10T06:23:25Z","abstract_excerpt":"Recently, Mahloujifar and Mahmoody (TCC'17) studied attacks against learning algorithms using a special case of Valiant's malicious noise, called $p$-tampering, in which the adversary gets to change any training example with independent probability $p$ but is limited to only choose malicious examples with correct labels. They obtained $p$-tampering attacks that increase the error probability in the so called targeted poisoning model in which the adversary's goal is to increase the loss of the trained hypothesis over a particular test example. At the heart of their attack was an efficient algor"},"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":"1711.03707","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-10T06:23:25Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"08da8113fcc19d74fb08ab7c0e474a0a857e175839f114d810ee6c8388c5bd62","abstract_canon_sha256":"a60c9eea7aae4d7eb3dec1784feccc8de495dd0d5fc197487c0c12c583641572"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:53.528471Z","signature_b64":"LnRrE4D0wu8xi81/mcSku3sjmF40O1GQ0YDFyQ4cYsDrq83CtDk6OMHkZXtZaXBp1cwNibPZ/I/LLpDWXXjzAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45d740edbcb9a0cca9e4bee4b70049a8b6243ba31ab1bccd0327b6309e857a43","last_reissued_at":"2026-05-17T23:59:53.527878Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:53.527878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning under $p$-Tampering Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Dimitrios I. Diochnos, Mohammad Mahmoody, Saeed Mahloujifar","submitted_at":"2017-11-10T06:23:25Z","abstract_excerpt":"Recently, Mahloujifar and Mahmoody (TCC'17) studied attacks against learning algorithms using a special case of Valiant's malicious noise, called $p$-tampering, in which the adversary gets to change any training example with independent probability $p$ but is limited to only choose malicious examples with correct labels. They obtained $p$-tampering attacks that increase the error probability in the so called targeted poisoning model in which the adversary's goal is to increase the loss of the trained hypothesis over a particular test example. At the heart of their attack was an efficient algor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.03707","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1711.03707","created_at":"2026-05-17T23:59:53.527980+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.03707v4","created_at":"2026-05-17T23:59:53.527980+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.03707","created_at":"2026-05-17T23:59:53.527980+00:00"},{"alias_kind":"pith_short_12","alias_value":"IXLUB3N4XGQM","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_16","alias_value":"IXLUB3N4XGQMZKPE","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_8","alias_value":"IXLUB3N4","created_at":"2026-05-18T12:31:21.493067+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/IXLUB3N4XGQMZKPEX3SLOACJVC","json":"https://pith.science/pith/IXLUB3N4XGQMZKPEX3SLOACJVC.json","graph_json":"https://pith.science/api/pith-number/IXLUB3N4XGQMZKPEX3SLOACJVC/graph.json","events_json":"https://pith.science/api/pith-number/IXLUB3N4XGQMZKPEX3SLOACJVC/events.json","paper":"https://pith.science/paper/IXLUB3N4"},"agent_actions":{"view_html":"https://pith.science/pith/IXLUB3N4XGQMZKPEX3SLOACJVC","download_json":"https://pith.science/pith/IXLUB3N4XGQMZKPEX3SLOACJVC.json","view_paper":"https://pith.science/paper/IXLUB3N4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.03707&json=true","fetch_graph":"https://pith.science/api/pith-number/IXLUB3N4XGQMZKPEX3SLOACJVC/graph.json","fetch_events":"https://pith.science/api/pith-number/IXLUB3N4XGQMZKPEX3SLOACJVC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IXLUB3N4XGQMZKPEX3SLOACJVC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IXLUB3N4XGQMZKPEX3SLOACJVC/action/storage_attestation","attest_author":"https://pith.science/pith/IXLUB3N4XGQMZKPEX3SLOACJVC/action/author_attestation","sign_citation":"https://pith.science/pith/IXLUB3N4XGQMZKPEX3SLOACJVC/action/citation_signature","submit_replication":"https://pith.science/pith/IXLUB3N4XGQMZKPEX3SLOACJVC/action/replication_record"}},"created_at":"2026-05-17T23:59:53.527980+00:00","updated_at":"2026-05-17T23:59:53.527980+00:00"}