{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:IGU4OR3PJ5NMB2W2FK4UIN7O25","short_pith_number":"pith:IGU4OR3P","schema_version":"1.0","canonical_sha256":"41a9c7476f4f5ac0eada2ab94437eed7401985a3c3252f110cb93137c32a6ddf","source":{"kind":"arxiv","id":"2004.05703","version":1},"attestation_state":"computed","paper":{"title":"DarkneTZ: Towards Model Privacy at the Edge using Trusted Execution Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ali Shahin Shamsabadi, Andrea Cavallaro, Fan Mo, Hamed Haddadi, Ilias Leontiadis, Kleomenis Katevas, Soteris Demetriou","submitted_at":"2020-04-12T21:42:03Z","abstract_excerpt":"We present DarkneTZ, a framework that uses an edge device's Trusted Execution Environment (TEE) in conjunction with model partitioning to limit the attack surface against Deep Neural Networks (DNNs). Increasingly, edge devices (smartphones and consumer IoT devices) are equipped with pre-trained DNNs for a variety of applications. This trend comes with privacy risks as models can leak information about their training data through effective membership inference attacks (MIAs). We evaluate the performance of DarkneTZ, including CPU execution time, memory usage, and accurate power consumption, usi"},"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":"2004.05703","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-12T21:42:03Z","cross_cats_sorted":["cs.CR","stat.ML"],"title_canon_sha256":"e4bdfcf16dbc493183948206abcfdb92d58b89082eb7fff0aa9ce3a5d61101a9","abstract_canon_sha256":"2b7dbf8e8280bedb5313f3c3adfab0ff162b75f4d5adb273301e18d7b1311c26"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:54:39.860847Z","signature_b64":"27yhrR/UOiZmtRZIGrG0gN5DPcVPENLnxCkmRwTM+2eMRl/81GZnfzASBNO2bkj7ngOiYpy94gqKX7GkE6o+Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41a9c7476f4f5ac0eada2ab94437eed7401985a3c3252f110cb93137c32a6ddf","last_reissued_at":"2026-07-05T00:54:39.860294Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:54:39.860294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DarkneTZ: Towards Model Privacy at the Edge using Trusted Execution Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ali Shahin Shamsabadi, Andrea Cavallaro, Fan Mo, Hamed Haddadi, Ilias Leontiadis, Kleomenis Katevas, Soteris Demetriou","submitted_at":"2020-04-12T21:42:03Z","abstract_excerpt":"We present DarkneTZ, a framework that uses an edge device's Trusted Execution Environment (TEE) in conjunction with model partitioning to limit the attack surface against Deep Neural Networks (DNNs). Increasingly, edge devices (smartphones and consumer IoT devices) are equipped with pre-trained DNNs for a variety of applications. This trend comes with privacy risks as models can leak information about their training data through effective membership inference attacks (MIAs). We evaluate the performance of DarkneTZ, including CPU execution time, memory usage, and accurate power consumption, usi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.05703","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/2004.05703/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":"2004.05703","created_at":"2026-07-05T00:54:39.860364+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.05703v1","created_at":"2026-07-05T00:54:39.860364+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.05703","created_at":"2026-07-05T00:54:39.860364+00:00"},{"alias_kind":"pith_short_12","alias_value":"IGU4OR3PJ5NM","created_at":"2026-07-05T00:54:39.860364+00:00"},{"alias_kind":"pith_short_16","alias_value":"IGU4OR3PJ5NMB2W2","created_at":"2026-07-05T00:54:39.860364+00:00"},{"alias_kind":"pith_short_8","alias_value":"IGU4OR3P","created_at":"2026-07-05T00:54:39.860364+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/IGU4OR3PJ5NMB2W2FK4UIN7O25","json":"https://pith.science/pith/IGU4OR3PJ5NMB2W2FK4UIN7O25.json","graph_json":"https://pith.science/api/pith-number/IGU4OR3PJ5NMB2W2FK4UIN7O25/graph.json","events_json":"https://pith.science/api/pith-number/IGU4OR3PJ5NMB2W2FK4UIN7O25/events.json","paper":"https://pith.science/paper/IGU4OR3P"},"agent_actions":{"view_html":"https://pith.science/pith/IGU4OR3PJ5NMB2W2FK4UIN7O25","download_json":"https://pith.science/pith/IGU4OR3PJ5NMB2W2FK4UIN7O25.json","view_paper":"https://pith.science/paper/IGU4OR3P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.05703&json=true","fetch_graph":"https://pith.science/api/pith-number/IGU4OR3PJ5NMB2W2FK4UIN7O25/graph.json","fetch_events":"https://pith.science/api/pith-number/IGU4OR3PJ5NMB2W2FK4UIN7O25/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IGU4OR3PJ5NMB2W2FK4UIN7O25/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IGU4OR3PJ5NMB2W2FK4UIN7O25/action/storage_attestation","attest_author":"https://pith.science/pith/IGU4OR3PJ5NMB2W2FK4UIN7O25/action/author_attestation","sign_citation":"https://pith.science/pith/IGU4OR3PJ5NMB2W2FK4UIN7O25/action/citation_signature","submit_replication":"https://pith.science/pith/IGU4OR3PJ5NMB2W2FK4UIN7O25/action/replication_record"}},"created_at":"2026-07-05T00:54:39.860364+00:00","updated_at":"2026-07-05T00:54:39.860364+00:00"}