{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:VC6A56SGSLH6UKPL2BHS5HPAFR","short_pith_number":"pith:VC6A56SG","schema_version":"1.0","canonical_sha256":"a8bc0efa4692cfea29ebd04f2e9de02c6b0595cad28164d4e537ba53dc10d148","source":{"kind":"arxiv","id":"1808.06809","version":1},"attestation_state":"computed","paper":{"title":"Are You Tampering With My Data?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Manuel Bouillon, Marcel W\\\"ursch, Marcus Liwicki, Mathias Seuret, Michele Alberti, Rolf Ingold, Vinaychandran Pondenkandath","submitted_at":"2018-08-21T09:08:56Z","abstract_excerpt":"We propose a novel approach towards adversarial attacks on neural networks (NN), focusing on tampering the data used for training instead of generating attacks on trained models. Our network-agnostic method creates a backdoor during training which can be exploited at test time to force a neural network to exhibit abnormal behaviour. We demonstrate on two widely used datasets (CIFAR-10 and SVHN) that a universal modification of just one pixel per image for all the images of a class in the training set is enough to corrupt the training procedure of several state-of-the-art deep neural networks c"},"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":"1808.06809","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-21T09:08:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ebdab6b86683358e12c2f4f443d221cae8f8ffc7f38516ab6f621869e675120b","abstract_canon_sha256":"ffb79f3ce32e8c4eec86729d19eefceaea0a917af25590611713f6b3e27bb17f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:39.016350Z","signature_b64":"YimVLMNLNQsx8l5ohtlna5qlhY5iCn/YGEb6h0IRYycDSp6m2QUNb+Lnz2xtzxOhr57mkGttAClmsKe0UhLTDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8bc0efa4692cfea29ebd04f2e9de02c6b0595cad28164d4e537ba53dc10d148","last_reissued_at":"2026-05-18T00:07:39.015770Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:39.015770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are You Tampering With My Data?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Manuel Bouillon, Marcel W\\\"ursch, Marcus Liwicki, Mathias Seuret, Michele Alberti, Rolf Ingold, Vinaychandran Pondenkandath","submitted_at":"2018-08-21T09:08:56Z","abstract_excerpt":"We propose a novel approach towards adversarial attacks on neural networks (NN), focusing on tampering the data used for training instead of generating attacks on trained models. Our network-agnostic method creates a backdoor during training which can be exploited at test time to force a neural network to exhibit abnormal behaviour. We demonstrate on two widely used datasets (CIFAR-10 and SVHN) that a universal modification of just one pixel per image for all the images of a class in the training set is enough to corrupt the training procedure of several state-of-the-art deep neural networks c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.06809","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":""},"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":"1808.06809","created_at":"2026-05-18T00:07:39.015847+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.06809v1","created_at":"2026-05-18T00:07:39.015847+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.06809","created_at":"2026-05-18T00:07:39.015847+00:00"},{"alias_kind":"pith_short_12","alias_value":"VC6A56SGSLH6","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"VC6A56SGSLH6UKPL","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"VC6A56SG","created_at":"2026-05-18T12:32:59.047623+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/VC6A56SGSLH6UKPL2BHS5HPAFR","json":"https://pith.science/pith/VC6A56SGSLH6UKPL2BHS5HPAFR.json","graph_json":"https://pith.science/api/pith-number/VC6A56SGSLH6UKPL2BHS5HPAFR/graph.json","events_json":"https://pith.science/api/pith-number/VC6A56SGSLH6UKPL2BHS5HPAFR/events.json","paper":"https://pith.science/paper/VC6A56SG"},"agent_actions":{"view_html":"https://pith.science/pith/VC6A56SGSLH6UKPL2BHS5HPAFR","download_json":"https://pith.science/pith/VC6A56SGSLH6UKPL2BHS5HPAFR.json","view_paper":"https://pith.science/paper/VC6A56SG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.06809&json=true","fetch_graph":"https://pith.science/api/pith-number/VC6A56SGSLH6UKPL2BHS5HPAFR/graph.json","fetch_events":"https://pith.science/api/pith-number/VC6A56SGSLH6UKPL2BHS5HPAFR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VC6A56SGSLH6UKPL2BHS5HPAFR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VC6A56SGSLH6UKPL2BHS5HPAFR/action/storage_attestation","attest_author":"https://pith.science/pith/VC6A56SGSLH6UKPL2BHS5HPAFR/action/author_attestation","sign_citation":"https://pith.science/pith/VC6A56SGSLH6UKPL2BHS5HPAFR/action/citation_signature","submit_replication":"https://pith.science/pith/VC6A56SGSLH6UKPL2BHS5HPAFR/action/replication_record"}},"created_at":"2026-05-18T00:07:39.015847+00:00","updated_at":"2026-05-18T00:07:39.015847+00:00"}