{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:2G5TGLIKS7M4GGTWUVCNAAYLJK","short_pith_number":"pith:2G5TGLIK","schema_version":"1.0","canonical_sha256":"d1bb332d0a97d9c31a76a544d0030b4ab092b15fde313f2299bef95ff3b1d3df","source":{"kind":"arxiv","id":"2006.14576","version":1},"attestation_state":"computed","paper":{"title":"Over-the-Air Membership Inference Attacks as Privacy Threats for Deep Learning-based Wireless Signal Classifiers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NI"],"primary_cat":"eess.SP","authors_text":"Kemal Davaslioglu, Yalin E. Sagduyu, Yi Shi","submitted_at":"2020-06-25T17:23:32Z","abstract_excerpt":"This paper presents how to leak private information from a wireless signal classifier by launching an over-the-air membership inference attack (MIA). As machine learning (ML) algorithms are used to process wireless signals to make decisions such as PHY-layer authentication, the training data characteristics (e.g., device-level information) and the environment conditions (e.g., channel information) under which the data is collected may leak to the ML model. As a privacy threat, the adversary can use this leaked information to exploit vulnerabilities of the ML model following an adversarial ML a"},"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":"2006.14576","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SP","submitted_at":"2020-06-25T17:23:32Z","cross_cats_sorted":["cs.NI"],"title_canon_sha256":"b85082b0faa27e1e4b9888861105f8ad95de1a9e44c4153312ec9a7898ebd9f1","abstract_canon_sha256":"fadbb1e3a210dd167230bd66f097a11f6c5b29ddddb1251de7999b9ccf749be5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:13:33.663597Z","signature_b64":"9chygY00vsNIPXyvFMVnycggD4Do96UACfTdbnJsfY2Ku6A4+nd836WneEj2NZMzH217YzQYpqa01uenEPIKAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1bb332d0a97d9c31a76a544d0030b4ab092b15fde313f2299bef95ff3b1d3df","last_reissued_at":"2026-07-05T01:13:33.663165Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:13:33.663165Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Over-the-Air Membership Inference Attacks as Privacy Threats for Deep Learning-based Wireless Signal Classifiers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NI"],"primary_cat":"eess.SP","authors_text":"Kemal Davaslioglu, Yalin E. Sagduyu, Yi Shi","submitted_at":"2020-06-25T17:23:32Z","abstract_excerpt":"This paper presents how to leak private information from a wireless signal classifier by launching an over-the-air membership inference attack (MIA). As machine learning (ML) algorithms are used to process wireless signals to make decisions such as PHY-layer authentication, the training data characteristics (e.g., device-level information) and the environment conditions (e.g., channel information) under which the data is collected may leak to the ML model. As a privacy threat, the adversary can use this leaked information to exploit vulnerabilities of the ML model following an adversarial ML a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.14576","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/2006.14576/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":"2006.14576","created_at":"2026-07-05T01:13:33.663230+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.14576v1","created_at":"2026-07-05T01:13:33.663230+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.14576","created_at":"2026-07-05T01:13:33.663230+00:00"},{"alias_kind":"pith_short_12","alias_value":"2G5TGLIKS7M4","created_at":"2026-07-05T01:13:33.663230+00:00"},{"alias_kind":"pith_short_16","alias_value":"2G5TGLIKS7M4GGTW","created_at":"2026-07-05T01:13:33.663230+00:00"},{"alias_kind":"pith_short_8","alias_value":"2G5TGLIK","created_at":"2026-07-05T01:13:33.663230+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.07188","citing_title":"Securing Genomic Data Against Inference Attacks in Federated Learning Environments","ref_index":48,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2G5TGLIKS7M4GGTWUVCNAAYLJK","json":"https://pith.science/pith/2G5TGLIKS7M4GGTWUVCNAAYLJK.json","graph_json":"https://pith.science/api/pith-number/2G5TGLIKS7M4GGTWUVCNAAYLJK/graph.json","events_json":"https://pith.science/api/pith-number/2G5TGLIKS7M4GGTWUVCNAAYLJK/events.json","paper":"https://pith.science/paper/2G5TGLIK"},"agent_actions":{"view_html":"https://pith.science/pith/2G5TGLIKS7M4GGTWUVCNAAYLJK","download_json":"https://pith.science/pith/2G5TGLIKS7M4GGTWUVCNAAYLJK.json","view_paper":"https://pith.science/paper/2G5TGLIK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.14576&json=true","fetch_graph":"https://pith.science/api/pith-number/2G5TGLIKS7M4GGTWUVCNAAYLJK/graph.json","fetch_events":"https://pith.science/api/pith-number/2G5TGLIKS7M4GGTWUVCNAAYLJK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2G5TGLIKS7M4GGTWUVCNAAYLJK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2G5TGLIKS7M4GGTWUVCNAAYLJK/action/storage_attestation","attest_author":"https://pith.science/pith/2G5TGLIKS7M4GGTWUVCNAAYLJK/action/author_attestation","sign_citation":"https://pith.science/pith/2G5TGLIKS7M4GGTWUVCNAAYLJK/action/citation_signature","submit_replication":"https://pith.science/pith/2G5TGLIKS7M4GGTWUVCNAAYLJK/action/replication_record"}},"created_at":"2026-07-05T01:13:33.663230+00:00","updated_at":"2026-07-05T01:13:33.663230+00:00"}