{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DELUIKMQH2ZIX6JJSGMIICCUP5","short_pith_number":"pith:DELUIKMQ","schema_version":"1.0","canonical_sha256":"19174429903eb28bf92991988408547f4110f69c13f538c3eccf9f47ced052e1","source":{"kind":"arxiv","id":"2407.11844","version":1},"attestation_state":"computed","paper":{"title":"Variational Randomized Smoothing for Sample-Wise Adversarial Robustness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jing Liu, Kieran Parsons, Ryo Hase, Toshiaki Koike-Akino, Ye Wang","submitted_at":"2024-07-16T15:25:13Z","abstract_excerpt":"Randomized smoothing is a defensive technique to achieve enhanced robustness against adversarial examples which are small input perturbations that degrade the performance of neural network models. Conventional randomized smoothing adds random noise with a fixed noise level for every input sample to smooth out adversarial perturbations. This paper proposes a new variational framework that uses a per-sample noise level suitable for each input by introducing a noise level selector. Our experimental results demonstrate enhancement of empirical robustness against adversarial attacks. We also provid"},"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":"2407.11844","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-16T15:25:13Z","cross_cats_sorted":["cs.AI","cs.CR","stat.ML"],"title_canon_sha256":"33470978e4ac74edcd82cce57009a9660e57533c9dc846fdb58b6cb84e604ddb","abstract_canon_sha256":"7d9f2ea884c103af4254ff15c4f0882998564031aa183466c6ec3d4bb53337df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:41.467080Z","signature_b64":"beShK//8CL7E5IRN9nBYvwiBDsujPgOCMDTv+rh7N4xd098/7obKlkOLFiV7bRTNpMwgdWHXnSklsEJXD23uCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19174429903eb28bf92991988408547f4110f69c13f538c3eccf9f47ced052e1","last_reissued_at":"2026-07-05T08:44:41.466672Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:41.466672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variational Randomized Smoothing for Sample-Wise Adversarial Robustness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jing Liu, Kieran Parsons, Ryo Hase, Toshiaki Koike-Akino, Ye Wang","submitted_at":"2024-07-16T15:25:13Z","abstract_excerpt":"Randomized smoothing is a defensive technique to achieve enhanced robustness against adversarial examples which are small input perturbations that degrade the performance of neural network models. Conventional randomized smoothing adds random noise with a fixed noise level for every input sample to smooth out adversarial perturbations. This paper proposes a new variational framework that uses a per-sample noise level suitable for each input by introducing a noise level selector. Our experimental results demonstrate enhancement of empirical robustness against adversarial attacks. We also provid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11844","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/2407.11844/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":"2407.11844","created_at":"2026-07-05T08:44:41.466737+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.11844v1","created_at":"2026-07-05T08:44:41.466737+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11844","created_at":"2026-07-05T08:44:41.466737+00:00"},{"alias_kind":"pith_short_12","alias_value":"DELUIKMQH2ZI","created_at":"2026-07-05T08:44:41.466737+00:00"},{"alias_kind":"pith_short_16","alias_value":"DELUIKMQH2ZIX6JJ","created_at":"2026-07-05T08:44:41.466737+00:00"},{"alias_kind":"pith_short_8","alias_value":"DELUIKMQ","created_at":"2026-07-05T08:44:41.466737+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/DELUIKMQH2ZIX6JJSGMIICCUP5","json":"https://pith.science/pith/DELUIKMQH2ZIX6JJSGMIICCUP5.json","graph_json":"https://pith.science/api/pith-number/DELUIKMQH2ZIX6JJSGMIICCUP5/graph.json","events_json":"https://pith.science/api/pith-number/DELUIKMQH2ZIX6JJSGMIICCUP5/events.json","paper":"https://pith.science/paper/DELUIKMQ"},"agent_actions":{"view_html":"https://pith.science/pith/DELUIKMQH2ZIX6JJSGMIICCUP5","download_json":"https://pith.science/pith/DELUIKMQH2ZIX6JJSGMIICCUP5.json","view_paper":"https://pith.science/paper/DELUIKMQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.11844&json=true","fetch_graph":"https://pith.science/api/pith-number/DELUIKMQH2ZIX6JJSGMIICCUP5/graph.json","fetch_events":"https://pith.science/api/pith-number/DELUIKMQH2ZIX6JJSGMIICCUP5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DELUIKMQH2ZIX6JJSGMIICCUP5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DELUIKMQH2ZIX6JJSGMIICCUP5/action/storage_attestation","attest_author":"https://pith.science/pith/DELUIKMQH2ZIX6JJSGMIICCUP5/action/author_attestation","sign_citation":"https://pith.science/pith/DELUIKMQH2ZIX6JJSGMIICCUP5/action/citation_signature","submit_replication":"https://pith.science/pith/DELUIKMQH2ZIX6JJSGMIICCUP5/action/replication_record"}},"created_at":"2026-07-05T08:44:41.466737+00:00","updated_at":"2026-07-05T08:44:41.466737+00:00"}