{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:TNT5DRHNI5V2X3643OL2SEMTET","short_pith_number":"pith:TNT5DRHN","schema_version":"1.0","canonical_sha256":"9b67d1c4ed476babefdcdb97a9119324e3b780557f7cc2458f435c2495b06c50","source":{"kind":"arxiv","id":"2003.09739","version":1},"attestation_state":"computed","paper":{"title":"New Security Challenges on Machine Learning Inference Engine: Chip Cloning and Model Reverse Engineering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.SP","authors_text":"Hongwu Jiang, Shanshi Huang, Shimeng Yu, Xiaochen Peng, Yandong Luo","submitted_at":"2020-03-21T19:58:14Z","abstract_excerpt":"Machine learning inference engine is of great interest to smart edge computing. Compute-in-memory (CIM) architecture has shown significant improvements in throughput and energy efficiency for hardware acceleration. Emerging non-volatile memory technologies offer great potential for instant on and off by dynamic power gating. Inference engine is typically pre-trained by the cloud and then being deployed to the filed. There are new attack models on chip cloning and neural network model reverse engineering. In this paper, we propose countermeasures to the weight cloning and input-output pair atta"},"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":"2003.09739","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SP","submitted_at":"2020-03-21T19:58:14Z","cross_cats_sorted":[],"title_canon_sha256":"ce6f2792f3f1dc6e82857d9aed45b97f363edb60286bd2b8cac91dadcda848b5","abstract_canon_sha256":"6c0e56b1a7ea1a9530c0293ce22a40925f025d35b99c92497b26b1015bd05265"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:49:46.523987Z","signature_b64":"gSyByLeIZVwz6GGKpwH9heDZadnQDZBguEfHYA8hMqST21xU34GszmPuXEtRQj3Dd3hEUmQGqDfWjxqjuqUnCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b67d1c4ed476babefdcdb97a9119324e3b780557f7cc2458f435c2495b06c50","last_reissued_at":"2026-07-05T00:49:46.523605Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:49:46.523605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"New Security Challenges on Machine Learning Inference Engine: Chip Cloning and Model Reverse Engineering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.SP","authors_text":"Hongwu Jiang, Shanshi Huang, Shimeng Yu, Xiaochen Peng, Yandong Luo","submitted_at":"2020-03-21T19:58:14Z","abstract_excerpt":"Machine learning inference engine is of great interest to smart edge computing. Compute-in-memory (CIM) architecture has shown significant improvements in throughput and energy efficiency for hardware acceleration. Emerging non-volatile memory technologies offer great potential for instant on and off by dynamic power gating. Inference engine is typically pre-trained by the cloud and then being deployed to the filed. There are new attack models on chip cloning and neural network model reverse engineering. In this paper, we propose countermeasures to the weight cloning and input-output pair atta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.09739","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/2003.09739/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":"2003.09739","created_at":"2026-07-05T00:49:46.523663+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.09739v1","created_at":"2026-07-05T00:49:46.523663+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.09739","created_at":"2026-07-05T00:49:46.523663+00:00"},{"alias_kind":"pith_short_12","alias_value":"TNT5DRHNI5V2","created_at":"2026-07-05T00:49:46.523663+00:00"},{"alias_kind":"pith_short_16","alias_value":"TNT5DRHNI5V2X364","created_at":"2026-07-05T00:49:46.523663+00:00"},{"alias_kind":"pith_short_8","alias_value":"TNT5DRHN","created_at":"2026-07-05T00:49:46.523663+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.13459","citing_title":"SoK: A Systems Perspective on Compound AI Threats and Countermeasures","ref_index":88,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TNT5DRHNI5V2X3643OL2SEMTET","json":"https://pith.science/pith/TNT5DRHNI5V2X3643OL2SEMTET.json","graph_json":"https://pith.science/api/pith-number/TNT5DRHNI5V2X3643OL2SEMTET/graph.json","events_json":"https://pith.science/api/pith-number/TNT5DRHNI5V2X3643OL2SEMTET/events.json","paper":"https://pith.science/paper/TNT5DRHN"},"agent_actions":{"view_html":"https://pith.science/pith/TNT5DRHNI5V2X3643OL2SEMTET","download_json":"https://pith.science/pith/TNT5DRHNI5V2X3643OL2SEMTET.json","view_paper":"https://pith.science/paper/TNT5DRHN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.09739&json=true","fetch_graph":"https://pith.science/api/pith-number/TNT5DRHNI5V2X3643OL2SEMTET/graph.json","fetch_events":"https://pith.science/api/pith-number/TNT5DRHNI5V2X3643OL2SEMTET/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TNT5DRHNI5V2X3643OL2SEMTET/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TNT5DRHNI5V2X3643OL2SEMTET/action/storage_attestation","attest_author":"https://pith.science/pith/TNT5DRHNI5V2X3643OL2SEMTET/action/author_attestation","sign_citation":"https://pith.science/pith/TNT5DRHNI5V2X3643OL2SEMTET/action/citation_signature","submit_replication":"https://pith.science/pith/TNT5DRHNI5V2X3643OL2SEMTET/action/replication_record"}},"created_at":"2026-07-05T00:49:46.523663+00:00","updated_at":"2026-07-05T00:49:46.523663+00:00"}