{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WDOZ2BEA4PNBKAIRZSXJ3IHVGX","short_pith_number":"pith:WDOZ2BEA","schema_version":"1.0","canonical_sha256":"b0dd9d0480e3da150111ccae9da0f535c18fb10a7cc5c6ea1beaea69020e2ebb","source":{"kind":"arxiv","id":"1905.09165","version":1},"attestation_state":"computed","paper":{"title":"A framework for the extraction of Deep Neural Networks by leveraging public data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aditya Kanade, Aditya Shukla, Shirish Shevade, Soham Pal, Vinod Ganapathy, Yash Gupta","submitted_at":"2019-05-22T14:26:04Z","abstract_excerpt":"Machine learning models trained on confidential datasets are increasingly being deployed for profit. Machine Learning as a Service (MLaaS) has made such models easily accessible to end-users. Prior work has developed model extraction attacks, in which an adversary extracts an approximation of MLaaS models by making black-box queries to it. However, none of these works is able to satisfy all the three essential criteria for practical model extraction: (1) the ability to work on deep learning models, (2) the non-requirement of domain knowledge and (3) the ability to work with a limited query bud"},"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":"1905.09165","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-22T14:26:04Z","cross_cats_sorted":["cs.AI","cs.CR","stat.ML"],"title_canon_sha256":"38c7e6e2dec0faa82bf9fca965ecbbe632f4a27170c66fe26d4569abd63b7509","abstract_canon_sha256":"806a616861cf9535b62af4e652e70aabc026d17dafd3c0582ce066a14d6a2df8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:21.789449Z","signature_b64":"khrPIGBbtLRhun4HQDEPnky7JcjIqlVsFroXbCwDGkKhNgtC/g0UwDG5Q5U9EmM5/gImSlg2O9EJwY3UD8ewAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0dd9d0480e3da150111ccae9da0f535c18fb10a7cc5c6ea1beaea69020e2ebb","last_reissued_at":"2026-05-17T23:45:21.788755Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:21.788755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A framework for the extraction of Deep Neural Networks by leveraging public data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aditya Kanade, Aditya Shukla, Shirish Shevade, Soham Pal, Vinod Ganapathy, Yash Gupta","submitted_at":"2019-05-22T14:26:04Z","abstract_excerpt":"Machine learning models trained on confidential datasets are increasingly being deployed for profit. Machine Learning as a Service (MLaaS) has made such models easily accessible to end-users. Prior work has developed model extraction attacks, in which an adversary extracts an approximation of MLaaS models by making black-box queries to it. However, none of these works is able to satisfy all the three essential criteria for practical model extraction: (1) the ability to work on deep learning models, (2) the non-requirement of domain knowledge and (3) the ability to work with a limited query bud"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.09165","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":"1905.09165","created_at":"2026-05-17T23:45:21.788870+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.09165v1","created_at":"2026-05-17T23:45:21.788870+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.09165","created_at":"2026-05-17T23:45:21.788870+00:00"},{"alias_kind":"pith_short_12","alias_value":"WDOZ2BEA4PNB","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"WDOZ2BEA4PNBKAIR","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"WDOZ2BEA","created_at":"2026-05-18T12:33:30.264802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2305.15717","citing_title":"The False Promise of Imitating Proprietary LLMs","ref_index":88,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WDOZ2BEA4PNBKAIRZSXJ3IHVGX","json":"https://pith.science/pith/WDOZ2BEA4PNBKAIRZSXJ3IHVGX.json","graph_json":"https://pith.science/api/pith-number/WDOZ2BEA4PNBKAIRZSXJ3IHVGX/graph.json","events_json":"https://pith.science/api/pith-number/WDOZ2BEA4PNBKAIRZSXJ3IHVGX/events.json","paper":"https://pith.science/paper/WDOZ2BEA"},"agent_actions":{"view_html":"https://pith.science/pith/WDOZ2BEA4PNBKAIRZSXJ3IHVGX","download_json":"https://pith.science/pith/WDOZ2BEA4PNBKAIRZSXJ3IHVGX.json","view_paper":"https://pith.science/paper/WDOZ2BEA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.09165&json=true","fetch_graph":"https://pith.science/api/pith-number/WDOZ2BEA4PNBKAIRZSXJ3IHVGX/graph.json","fetch_events":"https://pith.science/api/pith-number/WDOZ2BEA4PNBKAIRZSXJ3IHVGX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WDOZ2BEA4PNBKAIRZSXJ3IHVGX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WDOZ2BEA4PNBKAIRZSXJ3IHVGX/action/storage_attestation","attest_author":"https://pith.science/pith/WDOZ2BEA4PNBKAIRZSXJ3IHVGX/action/author_attestation","sign_citation":"https://pith.science/pith/WDOZ2BEA4PNBKAIRZSXJ3IHVGX/action/citation_signature","submit_replication":"https://pith.science/pith/WDOZ2BEA4PNBKAIRZSXJ3IHVGX/action/replication_record"}},"created_at":"2026-05-17T23:45:21.788870+00:00","updated_at":"2026-05-17T23:45:21.788870+00:00"}