{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:L6OPG344OYMLFCVVKQYINJ3ZKF","short_pith_number":"pith:L6OPG344","schema_version":"1.0","canonical_sha256":"5f9cf36f9c7618b28ab5543086a7795149e4209fed52d36202588f4ed0435f4b","source":{"kind":"arxiv","id":"2104.03414","version":3},"attestation_state":"computed","paper":{"title":"PrivateSNN: Privacy-Preserving Spiking Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Priyadarshini Panda, Yeshwanth Venkatesha, Youngeun Kim","submitted_at":"2021-04-07T22:14:02Z","abstract_excerpt":"How can we bring both privacy and energy-efficiency to a neural system? In this paper, we propose PrivateSNN, which aims to build low-power Spiking Neural Networks (SNNs) from a pre-trained ANN model without leaking sensitive information contained in a dataset. Here, we tackle two types of leakage problems: 1) Data leakage is caused when the networks access real training data during an ANN-SNN conversion process. 2) Class leakage is caused when class-related features can be reconstructed from network parameters. In order to address the data leakage issue, we generate synthetic images from the "},"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":"2104.03414","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-07T22:14:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"14dd0f18d4ce5a84627090a89a8718f83d41c1ea58f4e2eaaa9276589936fe0c","abstract_canon_sha256":"c42ec97d752f72cd8f160bae358cd50f6738b1e2a525094d1a7caa6982074153"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:25:09.726458Z","signature_b64":"tYmNb0iFWCK+FUp3dBUfGSYRVhmj/9w05/h+SjvQ3GzZyLreJq217HLLiWxC35baYu9K9iSa+JZyfhlgA/zsBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f9cf36f9c7618b28ab5543086a7795149e4209fed52d36202588f4ed0435f4b","last_reissued_at":"2026-07-05T04:25:09.725987Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:25:09.725987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PrivateSNN: Privacy-Preserving Spiking Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Priyadarshini Panda, Yeshwanth Venkatesha, Youngeun Kim","submitted_at":"2021-04-07T22:14:02Z","abstract_excerpt":"How can we bring both privacy and energy-efficiency to a neural system? In this paper, we propose PrivateSNN, which aims to build low-power Spiking Neural Networks (SNNs) from a pre-trained ANN model without leaking sensitive information contained in a dataset. Here, we tackle two types of leakage problems: 1) Data leakage is caused when the networks access real training data during an ANN-SNN conversion process. 2) Class leakage is caused when class-related features can be reconstructed from network parameters. In order to address the data leakage issue, we generate synthetic images from the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.03414","kind":"arxiv","version":3},"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/2104.03414/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":"2104.03414","created_at":"2026-07-05T04:25:09.726047+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.03414v3","created_at":"2026-07-05T04:25:09.726047+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.03414","created_at":"2026-07-05T04:25:09.726047+00:00"},{"alias_kind":"pith_short_12","alias_value":"L6OPG344OYML","created_at":"2026-07-05T04:25:09.726047+00:00"},{"alias_kind":"pith_short_16","alias_value":"L6OPG344OYMLFCVV","created_at":"2026-07-05T04:25:09.726047+00:00"},{"alias_kind":"pith_short_8","alias_value":"L6OPG344","created_at":"2026-07-05T04:25:09.726047+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/L6OPG344OYMLFCVVKQYINJ3ZKF","json":"https://pith.science/pith/L6OPG344OYMLFCVVKQYINJ3ZKF.json","graph_json":"https://pith.science/api/pith-number/L6OPG344OYMLFCVVKQYINJ3ZKF/graph.json","events_json":"https://pith.science/api/pith-number/L6OPG344OYMLFCVVKQYINJ3ZKF/events.json","paper":"https://pith.science/paper/L6OPG344"},"agent_actions":{"view_html":"https://pith.science/pith/L6OPG344OYMLFCVVKQYINJ3ZKF","download_json":"https://pith.science/pith/L6OPG344OYMLFCVVKQYINJ3ZKF.json","view_paper":"https://pith.science/paper/L6OPG344","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.03414&json=true","fetch_graph":"https://pith.science/api/pith-number/L6OPG344OYMLFCVVKQYINJ3ZKF/graph.json","fetch_events":"https://pith.science/api/pith-number/L6OPG344OYMLFCVVKQYINJ3ZKF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L6OPG344OYMLFCVVKQYINJ3ZKF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L6OPG344OYMLFCVVKQYINJ3ZKF/action/storage_attestation","attest_author":"https://pith.science/pith/L6OPG344OYMLFCVVKQYINJ3ZKF/action/author_attestation","sign_citation":"https://pith.science/pith/L6OPG344OYMLFCVVKQYINJ3ZKF/action/citation_signature","submit_replication":"https://pith.science/pith/L6OPG344OYMLFCVVKQYINJ3ZKF/action/replication_record"}},"created_at":"2026-07-05T04:25:09.726047+00:00","updated_at":"2026-07-05T04:25:09.726047+00:00"}