{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:RBCTNWIQV4YZ7AR6WMNAPHPBQT","short_pith_number":"pith:RBCTNWIQ","schema_version":"1.0","canonical_sha256":"884536d910af319f823eb31a079de184e7eaf80a2ad8a0b5f6b68482c81befa2","source":{"kind":"arxiv","id":"1810.03487","version":4},"attestation_state":"computed","paper":{"title":"Security Analysis of Deep Neural Networks Operating in the Presence of Cache Side-Channel Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Dana Dachman-Soled, Ian Rackow, Kevin Kulda, Michael Davinroy, Sanghyun Hong, Stuart Nevans Locke, Tudor Dumitra\\c{s}, Yi\\v{g}itcan Kaya","submitted_at":"2018-10-08T14:21:46Z","abstract_excerpt":"Recent work has introduced attacks that extract the architecture information of deep neural networks (DNN), as this knowledge enhances an adversary's capability to conduct black-box attacks against the model. This paper presents the first in-depth security analysis of DNN fingerprinting attacks that exploit cache side-channels. First, we define the threat model for these attacks: our adversary does not need the ability to query the victim model; instead, she runs a co-located process on the host machine victim's deep learning (DL) system is running and passively monitors the accesses of the ta"},"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":"1810.03487","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2018-10-08T14:21:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"74319f3f85940de5c3b7fc815932a90b4c852377a5544b3c6502cfc92bd46065","abstract_canon_sha256":"008d4e1a4f5ac8b696710d691d26304af2dcb92885da09c3008c3ea7a2e153ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:37:26.350639Z","signature_b64":"/5kT4HEAmXDi3QtQm284N5PMrSmw47Fz1QiiYX6GlVrDgFLN6Uav8ve9tyic6mJjmNVZizzTKxBLjn+t7IARDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"884536d910af319f823eb31a079de184e7eaf80a2ad8a0b5f6b68482c81befa2","last_reissued_at":"2026-07-05T00:37:26.350175Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:37:26.350175Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Security Analysis of Deep Neural Networks Operating in the Presence of Cache Side-Channel Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Dana Dachman-Soled, Ian Rackow, Kevin Kulda, Michael Davinroy, Sanghyun Hong, Stuart Nevans Locke, Tudor Dumitra\\c{s}, Yi\\v{g}itcan Kaya","submitted_at":"2018-10-08T14:21:46Z","abstract_excerpt":"Recent work has introduced attacks that extract the architecture information of deep neural networks (DNN), as this knowledge enhances an adversary's capability to conduct black-box attacks against the model. This paper presents the first in-depth security analysis of DNN fingerprinting attacks that exploit cache side-channels. First, we define the threat model for these attacks: our adversary does not need the ability to query the victim model; instead, she runs a co-located process on the host machine victim's deep learning (DL) system is running and passively monitors the accesses of the ta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.03487","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/1810.03487/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":"1810.03487","created_at":"2026-07-05T00:37:26.350240+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.03487v4","created_at":"2026-07-05T00:37:26.350240+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.03487","created_at":"2026-07-05T00:37:26.350240+00:00"},{"alias_kind":"pith_short_12","alias_value":"RBCTNWIQV4YZ","created_at":"2026-07-05T00:37:26.350240+00:00"},{"alias_kind":"pith_short_16","alias_value":"RBCTNWIQV4YZ7AR6","created_at":"2026-07-05T00:37:26.350240+00:00"},{"alias_kind":"pith_short_8","alias_value":"RBCTNWIQ","created_at":"2026-07-05T00:37:26.350240+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/RBCTNWIQV4YZ7AR6WMNAPHPBQT","json":"https://pith.science/pith/RBCTNWIQV4YZ7AR6WMNAPHPBQT.json","graph_json":"https://pith.science/api/pith-number/RBCTNWIQV4YZ7AR6WMNAPHPBQT/graph.json","events_json":"https://pith.science/api/pith-number/RBCTNWIQV4YZ7AR6WMNAPHPBQT/events.json","paper":"https://pith.science/paper/RBCTNWIQ"},"agent_actions":{"view_html":"https://pith.science/pith/RBCTNWIQV4YZ7AR6WMNAPHPBQT","download_json":"https://pith.science/pith/RBCTNWIQV4YZ7AR6WMNAPHPBQT.json","view_paper":"https://pith.science/paper/RBCTNWIQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.03487&json=true","fetch_graph":"https://pith.science/api/pith-number/RBCTNWIQV4YZ7AR6WMNAPHPBQT/graph.json","fetch_events":"https://pith.science/api/pith-number/RBCTNWIQV4YZ7AR6WMNAPHPBQT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RBCTNWIQV4YZ7AR6WMNAPHPBQT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RBCTNWIQV4YZ7AR6WMNAPHPBQT/action/storage_attestation","attest_author":"https://pith.science/pith/RBCTNWIQV4YZ7AR6WMNAPHPBQT/action/author_attestation","sign_citation":"https://pith.science/pith/RBCTNWIQV4YZ7AR6WMNAPHPBQT/action/citation_signature","submit_replication":"https://pith.science/pith/RBCTNWIQV4YZ7AR6WMNAPHPBQT/action/replication_record"}},"created_at":"2026-07-05T00:37:26.350240+00:00","updated_at":"2026-07-05T00:37:26.350240+00:00"}