{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:AMV575FGMB4A7FXVIOVI7ZTB7T","short_pith_number":"pith:AMV575FG","schema_version":"1.0","canonical_sha256":"032bdff4a660780f96f543aa8fe661fcfc240d2dcc78bd58f36baf62418f3b03","source":{"kind":"arxiv","id":"2009.06571","version":1},"attestation_state":"computed","paper":{"title":"Input Hessian Regularization of Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Marius Kloft, Robert A. Vandermeulen, Waleed Mustafa","submitted_at":"2020-09-14T16:58:16Z","abstract_excerpt":"Regularizing the input gradient has shown to be effective in promoting the robustness of neural networks. The regularization of the input's Hessian is therefore a natural next step. A key challenge here is the computational complexity. Computing the Hessian of inputs is computationally infeasible. In this paper we propose an efficient algorithm to train deep neural networks with Hessian operator-norm regularization. We analyze the approach theoretically and prove that the Hessian operator norm relates to the ability of a neural network to withstand an adversarial attack. We give a preliminary "},"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":"2009.06571","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-14T16:58:16Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"282ca02e07ae9587a57660af337f5e680df2245a25932d426e69aa0d068d9fe0","abstract_canon_sha256":"cd8465e352211456769ab158f1ea10b915779eb7800a5c7303d7f268c58cf457"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:35:09.682553Z","signature_b64":"jvQ3wy7jYAZyu2mUF3Qztp6pe2BXFchGaluzdYDq1ce9gtSmi2QcZCaTEPwlgPeJlXs6xoCLaoGjdEswb6f6Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"032bdff4a660780f96f543aa8fe661fcfc240d2dcc78bd58f36baf62418f3b03","last_reissued_at":"2026-07-05T01:35:09.682140Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:35:09.682140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Input Hessian Regularization of Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Marius Kloft, Robert A. Vandermeulen, Waleed Mustafa","submitted_at":"2020-09-14T16:58:16Z","abstract_excerpt":"Regularizing the input gradient has shown to be effective in promoting the robustness of neural networks. The regularization of the input's Hessian is therefore a natural next step. A key challenge here is the computational complexity. Computing the Hessian of inputs is computationally infeasible. In this paper we propose an efficient algorithm to train deep neural networks with Hessian operator-norm regularization. We analyze the approach theoretically and prove that the Hessian operator norm relates to the ability of a neural network to withstand an adversarial attack. We give a preliminary "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.06571","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/2009.06571/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":"2009.06571","created_at":"2026-07-05T01:35:09.682201+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.06571v1","created_at":"2026-07-05T01:35:09.682201+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.06571","created_at":"2026-07-05T01:35:09.682201+00:00"},{"alias_kind":"pith_short_12","alias_value":"AMV575FGMB4A","created_at":"2026-07-05T01:35:09.682201+00:00"},{"alias_kind":"pith_short_16","alias_value":"AMV575FGMB4A7FXV","created_at":"2026-07-05T01:35:09.682201+00:00"},{"alias_kind":"pith_short_8","alias_value":"AMV575FG","created_at":"2026-07-05T01:35:09.682201+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/AMV575FGMB4A7FXVIOVI7ZTB7T","json":"https://pith.science/pith/AMV575FGMB4A7FXVIOVI7ZTB7T.json","graph_json":"https://pith.science/api/pith-number/AMV575FGMB4A7FXVIOVI7ZTB7T/graph.json","events_json":"https://pith.science/api/pith-number/AMV575FGMB4A7FXVIOVI7ZTB7T/events.json","paper":"https://pith.science/paper/AMV575FG"},"agent_actions":{"view_html":"https://pith.science/pith/AMV575FGMB4A7FXVIOVI7ZTB7T","download_json":"https://pith.science/pith/AMV575FGMB4A7FXVIOVI7ZTB7T.json","view_paper":"https://pith.science/paper/AMV575FG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.06571&json=true","fetch_graph":"https://pith.science/api/pith-number/AMV575FGMB4A7FXVIOVI7ZTB7T/graph.json","fetch_events":"https://pith.science/api/pith-number/AMV575FGMB4A7FXVIOVI7ZTB7T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AMV575FGMB4A7FXVIOVI7ZTB7T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AMV575FGMB4A7FXVIOVI7ZTB7T/action/storage_attestation","attest_author":"https://pith.science/pith/AMV575FGMB4A7FXVIOVI7ZTB7T/action/author_attestation","sign_citation":"https://pith.science/pith/AMV575FGMB4A7FXVIOVI7ZTB7T/action/citation_signature","submit_replication":"https://pith.science/pith/AMV575FGMB4A7FXVIOVI7ZTB7T/action/replication_record"}},"created_at":"2026-07-05T01:35:09.682201+00:00","updated_at":"2026-07-05T01:35:09.682201+00:00"}