{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:GKE7GFFIGB3JV4JP3J7ZLLGOBE","short_pith_number":"pith:GKE7GFFI","canonical_record":{"source":{"id":"2107.14582","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-30T12:40:19Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"445b6d651d9e75f9adeda22057437ff9b35fa3facde70ad34799d28c2eadda4c","abstract_canon_sha256":"858da25179a363c2923074cbb169c1205709ce7f321a6d091d0370784295beb3"},"schema_version":"1.0"},"canonical_sha256":"3289f314a830769af12fda7f95acce091c9fa07919bd1cbeb06c5fca5092e784","source":{"kind":"arxiv","id":"2107.14582","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.14582","created_at":"2026-07-05T03:04:27Z"},{"alias_kind":"arxiv_version","alias_value":"2107.14582v3","created_at":"2026-07-05T03:04:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.14582","created_at":"2026-07-05T03:04:27Z"},{"alias_kind":"pith_short_12","alias_value":"GKE7GFFIGB3J","created_at":"2026-07-05T03:04:27Z"},{"alias_kind":"pith_short_16","alias_value":"GKE7GFFIGB3JV4JP","created_at":"2026-07-05T03:04:27Z"},{"alias_kind":"pith_short_8","alias_value":"GKE7GFFI","created_at":"2026-07-05T03:04:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:GKE7GFFIGB3JV4JP3J7ZLLGOBE","target":"record","payload":{"canonical_record":{"source":{"id":"2107.14582","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-30T12:40:19Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"445b6d651d9e75f9adeda22057437ff9b35fa3facde70ad34799d28c2eadda4c","abstract_canon_sha256":"858da25179a363c2923074cbb169c1205709ce7f321a6d091d0370784295beb3"},"schema_version":"1.0"},"canonical_sha256":"3289f314a830769af12fda7f95acce091c9fa07919bd1cbeb06c5fca5092e784","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:04:27.898660Z","signature_b64":"SPkVGD67Ec5nGgb6hM31wL/KQ4lcgeibscJfPMLnQ1Cb4ggG20MbnCrdmUgJzM0hc4WqCkbn9IFTvilQN8HcAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3289f314a830769af12fda7f95acce091c9fa07919bd1cbeb06c5fca5092e784","last_reissued_at":"2026-07-05T03:04:27.898335Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:04:27.898335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2107.14582","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:04:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Re4R9LBaBLLSy75dG4beFh9B2s80Fkrt1cV8eGk//wh65Zy2qZda7axht4AFoGpKQ2P/C3GwqaWSmoQUh3kBCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:22:39.747269Z"},"content_sha256":"1218f1cd11955099ecdbf9599f17718485d90d46808d2c434dcaa782989b3ba3","schema_version":"1.0","event_id":"sha256:1218f1cd11955099ecdbf9599f17718485d90d46808d2c434dcaa782989b3ba3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:GKE7GFFIGB3JV4JP3J7ZLLGOBE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"NeuralDP Differentially private neural networks by design","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Alexander Ziller, Daniel Rueckert, Dmitrii Usynin, Georgios Kaissis, Marcus R. Makowski, Moritz Knolle","submitted_at":"2021-07-30T12:40:19Z","abstract_excerpt":"The application of differential privacy to the training of deep neural networks holds the promise of allowing large-scale (decentralized) use of sensitive data while providing rigorous privacy guarantees to the individual. The predominant approach to differentially private training of neural networks is DP-SGD, which relies on norm-based gradient clipping as a method for bounding sensitivity, followed by the addition of appropriately calibrated Gaussian noise. In this work we propose NeuralDP, a technique for privatising activations of some layer within a neural network, which by the post-proc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.14582","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/2107.14582/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:04:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jgrpJgZ5xmt0KvOWzKUVr+T736WOO9IDQdu4r9HpLpVamqqdF5wIKEBe2R7L9p+6O1Xrg7vexkODeD1KDKCDBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:22:39.747747Z"},"content_sha256":"140e17fdc18530ab2abe93b1d69dd798bfebf5e3fa7df789124c777e3a7c68dc","schema_version":"1.0","event_id":"sha256:140e17fdc18530ab2abe93b1d69dd798bfebf5e3fa7df789124c777e3a7c68dc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GKE7GFFIGB3JV4JP3J7ZLLGOBE/bundle.json","state_url":"https://pith.science/pith/GKE7GFFIGB3JV4JP3J7ZLLGOBE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GKE7GFFIGB3JV4JP3J7ZLLGOBE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T10:22:39Z","links":{"resolver":"https://pith.science/pith/GKE7GFFIGB3JV4JP3J7ZLLGOBE","bundle":"https://pith.science/pith/GKE7GFFIGB3JV4JP3J7ZLLGOBE/bundle.json","state":"https://pith.science/pith/GKE7GFFIGB3JV4JP3J7ZLLGOBE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GKE7GFFIGB3JV4JP3J7ZLLGOBE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:GKE7GFFIGB3JV4JP3J7ZLLGOBE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"858da25179a363c2923074cbb169c1205709ce7f321a6d091d0370784295beb3","cross_cats_sorted":["cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-30T12:40:19Z","title_canon_sha256":"445b6d651d9e75f9adeda22057437ff9b35fa3facde70ad34799d28c2eadda4c"},"schema_version":"1.0","source":{"id":"2107.14582","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.14582","created_at":"2026-07-05T03:04:27Z"},{"alias_kind":"arxiv_version","alias_value":"2107.14582v3","created_at":"2026-07-05T03:04:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.14582","created_at":"2026-07-05T03:04:27Z"},{"alias_kind":"pith_short_12","alias_value":"GKE7GFFIGB3J","created_at":"2026-07-05T03:04:27Z"},{"alias_kind":"pith_short_16","alias_value":"GKE7GFFIGB3JV4JP","created_at":"2026-07-05T03:04:27Z"},{"alias_kind":"pith_short_8","alias_value":"GKE7GFFI","created_at":"2026-07-05T03:04:27Z"}],"graph_snapshots":[{"event_id":"sha256:140e17fdc18530ab2abe93b1d69dd798bfebf5e3fa7df789124c777e3a7c68dc","target":"graph","created_at":"2026-07-05T03:04:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2107.14582/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The application of differential privacy to the training of deep neural networks holds the promise of allowing large-scale (decentralized) use of sensitive data while providing rigorous privacy guarantees to the individual. The predominant approach to differentially private training of neural networks is DP-SGD, which relies on norm-based gradient clipping as a method for bounding sensitivity, followed by the addition of appropriately calibrated Gaussian noise. In this work we propose NeuralDP, a technique for privatising activations of some layer within a neural network, which by the post-proc","authors_text":"Alexander Ziller, Daniel Rueckert, Dmitrii Usynin, Georgios Kaissis, Marcus R. Makowski, Moritz Knolle","cross_cats":["cs.CR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-30T12:40:19Z","title":"NeuralDP Differentially private neural networks by design"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.14582","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1218f1cd11955099ecdbf9599f17718485d90d46808d2c434dcaa782989b3ba3","target":"record","created_at":"2026-07-05T03:04:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"858da25179a363c2923074cbb169c1205709ce7f321a6d091d0370784295beb3","cross_cats_sorted":["cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-30T12:40:19Z","title_canon_sha256":"445b6d651d9e75f9adeda22057437ff9b35fa3facde70ad34799d28c2eadda4c"},"schema_version":"1.0","source":{"id":"2107.14582","kind":"arxiv","version":3}},"canonical_sha256":"3289f314a830769af12fda7f95acce091c9fa07919bd1cbeb06c5fca5092e784","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3289f314a830769af12fda7f95acce091c9fa07919bd1cbeb06c5fca5092e784","first_computed_at":"2026-07-05T03:04:27.898335Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:04:27.898335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SPkVGD67Ec5nGgb6hM31wL/KQ4lcgeibscJfPMLnQ1Cb4ggG20MbnCrdmUgJzM0hc4WqCkbn9IFTvilQN8HcAw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:04:27.898660Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.14582","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1218f1cd11955099ecdbf9599f17718485d90d46808d2c434dcaa782989b3ba3","sha256:140e17fdc18530ab2abe93b1d69dd798bfebf5e3fa7df789124c777e3a7c68dc"],"state_sha256":"76f4af9e2347a52d17be41b756b8669aadb52eec1330dfa81b1b012788024438"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Co5r+otW9ihDr0heTr4XmiZqumaBI2CtRULdUbNa0Se6ryl/l7hkWSizE8wf9G5ofTgz85IxbqUpRzpVUudwAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T10:22:39.751183Z","bundle_sha256":"51f261c0086fb78b57fee7a3410da245c72cba15219c3719e72c82ef8d30e8d1"}}