{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PG6RYL23ZSGLX7ANW2DMJBK4ME","short_pith_number":"pith:PG6RYL23","schema_version":"1.0","canonical_sha256":"79bd1c2f5bcc8cbbfc0db686c4855c611e290a38845ce0b1bcef94dd9fd9d970","source":{"kind":"arxiv","id":"2411.09945","version":1},"attestation_state":"computed","paper":{"title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"Ding Li, Mengyu Yao, Xiangqun Chen, Yao Guo, Yifeng Cai, Ziqi Zhang","submitted_at":"2024-11-15T04:52:11Z","abstract_excerpt":"Trusted Execution Environments (TEE) are used to safeguard on-device models. However, directly employing TEEs to secure the entire DNN model is challenging due to the limited computational speed. Utilizing GPU can accelerate DNN's computation speed but commercial widely-available GPUs usually lack security protection. To this end, scholars introduce TSDP, a method that protects privacy-sensitive weights within TEEs and offloads insensitive weights to GPUs. Nevertheless, current methods do not consider the presence of a knowledgeable adversary who can access abundant publicly available pre-trai"},"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":"2411.09945","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-11-15T04:52:11Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d47cafd822a797dcc816fd1e427a90ab6d01b5c965f702181d82323e6127e0f4","abstract_canon_sha256":"fa41c4c8ea8eeb7785bc20a4cfa80afef41b9d0ff2fe17aab7c11d346a4cf470"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:35:56.128746Z","signature_b64":"wUTrrKX+9Vl5vcO1aGT47i9M2G2Ohx8hgspnnlWnVWtkoZ+oMHoKmZefw3ndsFDlJmGWWWiQYUWptT2F02kVCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79bd1c2f5bcc8cbbfc0db686c4855c611e290a38845ce0b1bcef94dd9fd9d970","last_reissued_at":"2026-07-05T09:35:56.128235Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:35:56.128235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"Ding Li, Mengyu Yao, Xiangqun Chen, Yao Guo, Yifeng Cai, Ziqi Zhang","submitted_at":"2024-11-15T04:52:11Z","abstract_excerpt":"Trusted Execution Environments (TEE) are used to safeguard on-device models. However, directly employing TEEs to secure the entire DNN model is challenging due to the limited computational speed. Utilizing GPU can accelerate DNN's computation speed but commercial widely-available GPUs usually lack security protection. To this end, scholars introduce TSDP, a method that protects privacy-sensitive weights within TEEs and offloads insensitive weights to GPUs. Nevertheless, current methods do not consider the presence of a knowledgeable adversary who can access abundant publicly available pre-trai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.09945","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/2411.09945/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":"2411.09945","created_at":"2026-07-05T09:35:56.128297+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.09945v1","created_at":"2026-07-05T09:35:56.128297+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.09945","created_at":"2026-07-05T09:35:56.128297+00:00"},{"alias_kind":"pith_short_12","alias_value":"PG6RYL23ZSGL","created_at":"2026-07-05T09:35:56.128297+00:00"},{"alias_kind":"pith_short_16","alias_value":"PG6RYL23ZSGLX7AN","created_at":"2026-07-05T09:35:56.128297+00:00"},{"alias_kind":"pith_short_8","alias_value":"PG6RYL23","created_at":"2026-07-05T09:35:56.128297+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.03213","citing_title":"When Agents Handle Secrets: A Survey of Confidential Computing for Agentic AI","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03213","citing_title":"When Agents Handle Secrets: A Survey of Confidential Computing for Agentic AI","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PG6RYL23ZSGLX7ANW2DMJBK4ME","json":"https://pith.science/pith/PG6RYL23ZSGLX7ANW2DMJBK4ME.json","graph_json":"https://pith.science/api/pith-number/PG6RYL23ZSGLX7ANW2DMJBK4ME/graph.json","events_json":"https://pith.science/api/pith-number/PG6RYL23ZSGLX7ANW2DMJBK4ME/events.json","paper":"https://pith.science/paper/PG6RYL23"},"agent_actions":{"view_html":"https://pith.science/pith/PG6RYL23ZSGLX7ANW2DMJBK4ME","download_json":"https://pith.science/pith/PG6RYL23ZSGLX7ANW2DMJBK4ME.json","view_paper":"https://pith.science/paper/PG6RYL23","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.09945&json=true","fetch_graph":"https://pith.science/api/pith-number/PG6RYL23ZSGLX7ANW2DMJBK4ME/graph.json","fetch_events":"https://pith.science/api/pith-number/PG6RYL23ZSGLX7ANW2DMJBK4ME/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PG6RYL23ZSGLX7ANW2DMJBK4ME/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PG6RYL23ZSGLX7ANW2DMJBK4ME/action/storage_attestation","attest_author":"https://pith.science/pith/PG6RYL23ZSGLX7ANW2DMJBK4ME/action/author_attestation","sign_citation":"https://pith.science/pith/PG6RYL23ZSGLX7ANW2DMJBK4ME/action/citation_signature","submit_replication":"https://pith.science/pith/PG6RYL23ZSGLX7ANW2DMJBK4ME/action/replication_record"}},"created_at":"2026-07-05T09:35:56.128297+00:00","updated_at":"2026-07-05T09:35:56.128297+00:00"}