{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:B7JIEPVBGE5TX7PA2BOPSTML63","short_pith_number":"pith:B7JIEPVB","schema_version":"1.0","canonical_sha256":"0fd2823ea1313b3bfde0d05cf94d8bf6eb5f78ebc0b98a1406ee3280ccce8c15","source":{"kind":"arxiv","id":"2606.27704","version":1},"attestation_state":"computed","paper":{"title":"AdvScan: Black-Box Adversarial Example Detection at Runtime through Power Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Michael Zuzak, Robi Paul","submitted_at":"2026-06-26T04:04:08Z","abstract_excerpt":"TinyML models deployed on edge devices are increasingly adopted in safety/security-critical applications, making them a prime target for adversarial example (AE) attacks where inputs are modified to cause misclassifications. However, existing AE detection methods either require white-box model access, which is often unavailable in licensed black-box deployments, or rely on input pre-processing stages that add non-trivial latency and resource overhead, often exceeding what mission-critical applications can afford on their inference path. To address these challenges, we propose AdvScan, a runtim"},"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":"2606.27704","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2026-06-26T04:04:08Z","cross_cats_sorted":[],"title_canon_sha256":"b5d535f3e0b7a8e98c384b45ddbc13751bec3bcc7c9f673996538fbc609f750d","abstract_canon_sha256":"6a74b5c9c006a7623d8f788e041d71f0b3d04edb360fe314c6a441b1e2c2acff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:14:45.949218Z","signature_b64":"WG0ZCJtZN4/tCak9NAXe9g9HlMp67maqdHuxPvnh2SxwtPhAToDrOGb5Kz06Bkd3hpvzH8X0yhsqJfcgTEuiDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fd2823ea1313b3bfde0d05cf94d8bf6eb5f78ebc0b98a1406ee3280ccce8c15","last_reissued_at":"2026-06-29T01:14:45.948866Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:14:45.948866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AdvScan: Black-Box Adversarial Example Detection at Runtime through Power Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Michael Zuzak, Robi Paul","submitted_at":"2026-06-26T04:04:08Z","abstract_excerpt":"TinyML models deployed on edge devices are increasingly adopted in safety/security-critical applications, making them a prime target for adversarial example (AE) attacks where inputs are modified to cause misclassifications. However, existing AE detection methods either require white-box model access, which is often unavailable in licensed black-box deployments, or rely on input pre-processing stages that add non-trivial latency and resource overhead, often exceeding what mission-critical applications can afford on their inference path. To address these challenges, we propose AdvScan, a runtim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27704","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/2606.27704/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":"2606.27704","created_at":"2026-06-29T01:14:45.948920+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.27704v1","created_at":"2026-06-29T01:14:45.948920+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27704","created_at":"2026-06-29T01:14:45.948920+00:00"},{"alias_kind":"pith_short_12","alias_value":"B7JIEPVBGE5T","created_at":"2026-06-29T01:14:45.948920+00:00"},{"alias_kind":"pith_short_16","alias_value":"B7JIEPVBGE5TX7PA","created_at":"2026-06-29T01:14:45.948920+00:00"},{"alias_kind":"pith_short_8","alias_value":"B7JIEPVB","created_at":"2026-06-29T01:14:45.948920+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/B7JIEPVBGE5TX7PA2BOPSTML63","json":"https://pith.science/pith/B7JIEPVBGE5TX7PA2BOPSTML63.json","graph_json":"https://pith.science/api/pith-number/B7JIEPVBGE5TX7PA2BOPSTML63/graph.json","events_json":"https://pith.science/api/pith-number/B7JIEPVBGE5TX7PA2BOPSTML63/events.json","paper":"https://pith.science/paper/B7JIEPVB"},"agent_actions":{"view_html":"https://pith.science/pith/B7JIEPVBGE5TX7PA2BOPSTML63","download_json":"https://pith.science/pith/B7JIEPVBGE5TX7PA2BOPSTML63.json","view_paper":"https://pith.science/paper/B7JIEPVB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.27704&json=true","fetch_graph":"https://pith.science/api/pith-number/B7JIEPVBGE5TX7PA2BOPSTML63/graph.json","fetch_events":"https://pith.science/api/pith-number/B7JIEPVBGE5TX7PA2BOPSTML63/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B7JIEPVBGE5TX7PA2BOPSTML63/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B7JIEPVBGE5TX7PA2BOPSTML63/action/storage_attestation","attest_author":"https://pith.science/pith/B7JIEPVBGE5TX7PA2BOPSTML63/action/author_attestation","sign_citation":"https://pith.science/pith/B7JIEPVBGE5TX7PA2BOPSTML63/action/citation_signature","submit_replication":"https://pith.science/pith/B7JIEPVBGE5TX7PA2BOPSTML63/action/replication_record"}},"created_at":"2026-06-29T01:14:45.948920+00:00","updated_at":"2026-06-29T01:14:45.948920+00:00"}