{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2M2R7PX2CB4Z5YYOVFH5XJN4L5","short_pith_number":"pith:2M2R7PX2","schema_version":"1.0","canonical_sha256":"d3351fbefa10799ee30ea94fdba5bc5f511932881dfb0fc282438ead2aa423c4","source":{"kind":"arxiv","id":"2204.08189","version":4},"attestation_state":"computed","paper":{"title":"Sardino: Ultra-Fast Dynamic Ensemble for Secure Visual Sensing at Mobile Edge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qun Song, Rui Tan, Wenjie Luo, Zhenyu Yan","submitted_at":"2022-04-18T06:54:48Z","abstract_excerpt":"Adversarial example attack endangers the mobile edge systems such as vehicles and drones that adopt deep neural networks for visual sensing. This paper presents {\\em Sardino}, an active and dynamic defense approach that renews the inference ensemble at run time to develop security against the adaptive adversary who tries to exfiltrate the ensemble and construct the corresponding effective adversarial examples. By applying consistency check and data fusion on the ensemble's predictions, Sardino can detect and thwart adversarial inputs. Compared with the training-based ensemble renewal, we use H"},"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":"2204.08189","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-18T06:54:48Z","cross_cats_sorted":[],"title_canon_sha256":"a4bcf934a29637422f34d65c638d62085f75bbf848b0947b2a2ecfc4b5e95ef8","abstract_canon_sha256":"497fc55789319a6a54f9be580fb9ce70d94bbf718ae7b1cb2f533d003987fe65"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:11:38.425481Z","signature_b64":"nEi6mrA6hgxkg65ZJjIPwYyMsOphaUra6VMQli4qr5MEVRe1kzeYKTuaxQ1SI9+lTmQvQzStvsxv2ToLR3t9AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3351fbefa10799ee30ea94fdba5bc5f511932881dfb0fc282438ead2aa423c4","last_reissued_at":"2026-07-05T05:11:38.425052Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:11:38.425052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sardino: Ultra-Fast Dynamic Ensemble for Secure Visual Sensing at Mobile Edge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qun Song, Rui Tan, Wenjie Luo, Zhenyu Yan","submitted_at":"2022-04-18T06:54:48Z","abstract_excerpt":"Adversarial example attack endangers the mobile edge systems such as vehicles and drones that adopt deep neural networks for visual sensing. This paper presents {\\em Sardino}, an active and dynamic defense approach that renews the inference ensemble at run time to develop security against the adaptive adversary who tries to exfiltrate the ensemble and construct the corresponding effective adversarial examples. By applying consistency check and data fusion on the ensemble's predictions, Sardino can detect and thwart adversarial inputs. Compared with the training-based ensemble renewal, we use H"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.08189","kind":"arxiv","version":4},"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/2204.08189/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":"2204.08189","created_at":"2026-07-05T05:11:38.425109+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.08189v4","created_at":"2026-07-05T05:11:38.425109+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.08189","created_at":"2026-07-05T05:11:38.425109+00:00"},{"alias_kind":"pith_short_12","alias_value":"2M2R7PX2CB4Z","created_at":"2026-07-05T05:11:38.425109+00:00"},{"alias_kind":"pith_short_16","alias_value":"2M2R7PX2CB4Z5YYO","created_at":"2026-07-05T05:11:38.425109+00:00"},{"alias_kind":"pith_short_8","alias_value":"2M2R7PX2","created_at":"2026-07-05T05:11:38.425109+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/2M2R7PX2CB4Z5YYOVFH5XJN4L5","json":"https://pith.science/pith/2M2R7PX2CB4Z5YYOVFH5XJN4L5.json","graph_json":"https://pith.science/api/pith-number/2M2R7PX2CB4Z5YYOVFH5XJN4L5/graph.json","events_json":"https://pith.science/api/pith-number/2M2R7PX2CB4Z5YYOVFH5XJN4L5/events.json","paper":"https://pith.science/paper/2M2R7PX2"},"agent_actions":{"view_html":"https://pith.science/pith/2M2R7PX2CB4Z5YYOVFH5XJN4L5","download_json":"https://pith.science/pith/2M2R7PX2CB4Z5YYOVFH5XJN4L5.json","view_paper":"https://pith.science/paper/2M2R7PX2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.08189&json=true","fetch_graph":"https://pith.science/api/pith-number/2M2R7PX2CB4Z5YYOVFH5XJN4L5/graph.json","fetch_events":"https://pith.science/api/pith-number/2M2R7PX2CB4Z5YYOVFH5XJN4L5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2M2R7PX2CB4Z5YYOVFH5XJN4L5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2M2R7PX2CB4Z5YYOVFH5XJN4L5/action/storage_attestation","attest_author":"https://pith.science/pith/2M2R7PX2CB4Z5YYOVFH5XJN4L5/action/author_attestation","sign_citation":"https://pith.science/pith/2M2R7PX2CB4Z5YYOVFH5XJN4L5/action/citation_signature","submit_replication":"https://pith.science/pith/2M2R7PX2CB4Z5YYOVFH5XJN4L5/action/replication_record"}},"created_at":"2026-07-05T05:11:38.425109+00:00","updated_at":"2026-07-05T05:11:38.425109+00:00"}