{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:RFGEHDBFPZR6GGUEFUYYWICVSD","short_pith_number":"pith:RFGEHDBF","schema_version":"1.0","canonical_sha256":"894c438c257e63e31a842d318b205590ca6a0a0c92d40238f5398c290ca66558","source":{"kind":"arxiv","id":"1806.05476","version":1},"attestation_state":"computed","paper":{"title":"Copycat CNN: Stealing Knowledge by Persuading Confession with Random Non-Labeled Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CV","authors_text":"Alberto F. De Souza, Claudine Badue, Jacson Rodrigues Correia-Silva, Rodrigo F. Berriel, Thiago Oliveira-Santos","submitted_at":"2018-06-14T11:32:27Z","abstract_excerpt":"In the past few years, Convolutional Neural Networks (CNNs) have been achieving state-of-the-art performance on a variety of problems. Many companies employ resources and money to generate these models and provide them as an API, therefore it is in their best interest to protect them, i.e., to avoid that someone else copies them. Recent studies revealed that state-of-the-art CNNs are vulnerable to adversarial examples attacks, and this weakness indicates that CNNs do not need to operate in the problem domain (PD). Therefore, we hypothesize that they also do not need to be trained with examples"},"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":"1806.05476","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-14T11:32:27Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7265913a5ac37b893aad9399a3c8404862bbcce514c024bb59a235fe309319fe","abstract_canon_sha256":"ed5e49aa3532bb5bb2c678c244b6ed4d369976643e4dffc45979d7d83780c3f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:44.720462Z","signature_b64":"d4WbpRHORmnhDWWXU2sp9vW+rJk7nlWQ2tcza1d8Q7LY9bmcb9Do3Ir3sXoxZ6gwZsVJdLMOGUe2bCzUUayEDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"894c438c257e63e31a842d318b205590ca6a0a0c92d40238f5398c290ca66558","last_reissued_at":"2026-05-18T00:02:44.720022Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:44.720022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Copycat CNN: Stealing Knowledge by Persuading Confession with Random Non-Labeled Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CV","authors_text":"Alberto F. De Souza, Claudine Badue, Jacson Rodrigues Correia-Silva, Rodrigo F. Berriel, Thiago Oliveira-Santos","submitted_at":"2018-06-14T11:32:27Z","abstract_excerpt":"In the past few years, Convolutional Neural Networks (CNNs) have been achieving state-of-the-art performance on a variety of problems. Many companies employ resources and money to generate these models and provide them as an API, therefore it is in their best interest to protect them, i.e., to avoid that someone else copies them. Recent studies revealed that state-of-the-art CNNs are vulnerable to adversarial examples attacks, and this weakness indicates that CNNs do not need to operate in the problem domain (PD). Therefore, we hypothesize that they also do not need to be trained with examples"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.05476","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":"1806.05476","created_at":"2026-05-18T00:02:44.720091+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.05476v1","created_at":"2026-05-18T00:02:44.720091+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.05476","created_at":"2026-05-18T00:02:44.720091+00:00"},{"alias_kind":"pith_short_12","alias_value":"RFGEHDBFPZR6","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"RFGEHDBFPZR6GGUE","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"RFGEHDBF","created_at":"2026-05-18T12:32:50.500415+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/RFGEHDBFPZR6GGUEFUYYWICVSD","json":"https://pith.science/pith/RFGEHDBFPZR6GGUEFUYYWICVSD.json","graph_json":"https://pith.science/api/pith-number/RFGEHDBFPZR6GGUEFUYYWICVSD/graph.json","events_json":"https://pith.science/api/pith-number/RFGEHDBFPZR6GGUEFUYYWICVSD/events.json","paper":"https://pith.science/paper/RFGEHDBF"},"agent_actions":{"view_html":"https://pith.science/pith/RFGEHDBFPZR6GGUEFUYYWICVSD","download_json":"https://pith.science/pith/RFGEHDBFPZR6GGUEFUYYWICVSD.json","view_paper":"https://pith.science/paper/RFGEHDBF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.05476&json=true","fetch_graph":"https://pith.science/api/pith-number/RFGEHDBFPZR6GGUEFUYYWICVSD/graph.json","fetch_events":"https://pith.science/api/pith-number/RFGEHDBFPZR6GGUEFUYYWICVSD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RFGEHDBFPZR6GGUEFUYYWICVSD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RFGEHDBFPZR6GGUEFUYYWICVSD/action/storage_attestation","attest_author":"https://pith.science/pith/RFGEHDBFPZR6GGUEFUYYWICVSD/action/author_attestation","sign_citation":"https://pith.science/pith/RFGEHDBFPZR6GGUEFUYYWICVSD/action/citation_signature","submit_replication":"https://pith.science/pith/RFGEHDBFPZR6GGUEFUYYWICVSD/action/replication_record"}},"created_at":"2026-05-18T00:02:44.720091+00:00","updated_at":"2026-05-18T00:02:44.720091+00:00"}