{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YK3RHDCVWOPIU3WWBG5BKZMAQB","short_pith_number":"pith:YK3RHDCV","schema_version":"1.0","canonical_sha256":"c2b7138c55b39e8a6ed609ba15658080648315410072fe959b0608371d46f8f2","source":{"kind":"arxiv","id":"2606.07470","version":1},"attestation_state":"computed","paper":{"title":"Verifiable and Confidential DNN Inference on Low-End Edge Devices","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Aur\\'elien Francillon (EURECOM), Ivan De Oliveira Nunes (University of Zurich), Mohamed Khalil Kiri (EURECOM), Norrathep Rattanavipanon (PSU Phuket)","submitted_at":"2026-06-05T17:23:39Z","abstract_excerpt":"Deploying deep neural network (DNN) inference on low-end edge devices raises two key challenges: protecting model confidentiality against a potentially compromised edge system and enabling verifiable inference without incurring prohibitive overhead. Existing approaches either house partial models and inference software within trusted execution environments (TEEs), resulting in high cost and an application-dependent trusted computing base (TCB), or execute in untrusted environments, providing little security.\n  In this work, we present VECODI, a framework for verifiable and confidential DNN inf"},"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":"2606.07470","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-06-05T17:23:39Z","cross_cats_sorted":[],"title_canon_sha256":"ac663e74f7e9bec85836cd60c6a5a7f77ae414b67a2c31c9ac7be8be3046b500","abstract_canon_sha256":"3e7a5b12c9776cb5b7b2eb292b0fcd358d04543dc468f97b1f88100d68297e4a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:05:28.973432Z","signature_b64":"nBhg/6kbRZGCviTMnX5/e2Ohu2VGhWPEZU0mG9MDfzS++xz2GmZnKqNCoMOS6uyRYdhhnCFV8+QDgX43EiFnDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2b7138c55b39e8a6ed609ba15658080648315410072fe959b0608371d46f8f2","last_reissued_at":"2026-06-08T01:05:28.972476Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:05:28.972476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Verifiable and Confidential DNN Inference on Low-End Edge Devices","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Aur\\'elien Francillon (EURECOM), Ivan De Oliveira Nunes (University of Zurich), Mohamed Khalil Kiri (EURECOM), Norrathep Rattanavipanon (PSU Phuket)","submitted_at":"2026-06-05T17:23:39Z","abstract_excerpt":"Deploying deep neural network (DNN) inference on low-end edge devices raises two key challenges: protecting model confidentiality against a potentially compromised edge system and enabling verifiable inference without incurring prohibitive overhead. Existing approaches either house partial models and inference software within trusted execution environments (TEEs), resulting in high cost and an application-dependent trusted computing base (TCB), or execute in untrusted environments, providing little security.\n  In this work, we present VECODI, a framework for verifiable and confidential DNN inf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07470","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/2606.07470/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":"2606.07470","created_at":"2026-06-08T01:05:28.972634+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07470v1","created_at":"2026-06-08T01:05:28.972634+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07470","created_at":"2026-06-08T01:05:28.972634+00:00"},{"alias_kind":"pith_short_12","alias_value":"YK3RHDCVWOPI","created_at":"2026-06-08T01:05:28.972634+00:00"},{"alias_kind":"pith_short_16","alias_value":"YK3RHDCVWOPIU3WW","created_at":"2026-06-08T01:05:28.972634+00:00"},{"alias_kind":"pith_short_8","alias_value":"YK3RHDCV","created_at":"2026-06-08T01:05:28.972634+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/YK3RHDCVWOPIU3WWBG5BKZMAQB","json":"https://pith.science/pith/YK3RHDCVWOPIU3WWBG5BKZMAQB.json","graph_json":"https://pith.science/api/pith-number/YK3RHDCVWOPIU3WWBG5BKZMAQB/graph.json","events_json":"https://pith.science/api/pith-number/YK3RHDCVWOPIU3WWBG5BKZMAQB/events.json","paper":"https://pith.science/paper/YK3RHDCV"},"agent_actions":{"view_html":"https://pith.science/pith/YK3RHDCVWOPIU3WWBG5BKZMAQB","download_json":"https://pith.science/pith/YK3RHDCVWOPIU3WWBG5BKZMAQB.json","view_paper":"https://pith.science/paper/YK3RHDCV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07470&json=true","fetch_graph":"https://pith.science/api/pith-number/YK3RHDCVWOPIU3WWBG5BKZMAQB/graph.json","fetch_events":"https://pith.science/api/pith-number/YK3RHDCVWOPIU3WWBG5BKZMAQB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YK3RHDCVWOPIU3WWBG5BKZMAQB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YK3RHDCVWOPIU3WWBG5BKZMAQB/action/storage_attestation","attest_author":"https://pith.science/pith/YK3RHDCVWOPIU3WWBG5BKZMAQB/action/author_attestation","sign_citation":"https://pith.science/pith/YK3RHDCVWOPIU3WWBG5BKZMAQB/action/citation_signature","submit_replication":"https://pith.science/pith/YK3RHDCVWOPIU3WWBG5BKZMAQB/action/replication_record"}},"created_at":"2026-06-08T01:05:28.972634+00:00","updated_at":"2026-06-08T01:05:28.972634+00:00"}