{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KY4QVC6KVWTJB4DIDQUWSPS77C","short_pith_number":"pith:KY4QVC6K","schema_version":"1.0","canonical_sha256":"56390a8bcaada690f0681c29693e5ff89567da51c6c6a9184cb000c652974f96","source":{"kind":"arxiv","id":"2110.13950","version":1},"attestation_state":"computed","paper":{"title":"Can't Fool Me: Adversarially Robust Transformer for Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Divya Choudhary, Palash Goyal, Saurabh Sahu","submitted_at":"2021-10-26T18:30:21Z","abstract_excerpt":"Deep neural networks have been shown to perform poorly on adversarial examples. To address this, several techniques have been proposed to increase robustness of a model for image classification tasks. However, in video understanding tasks, developing adversarially robust models is still unexplored. In this paper, we aim to bridge this gap. We first show that simple extensions of image based adversarially robust models slightly improve the worst-case performance. Further, we propose a temporal attention regularization scheme in Transformer to improve the robustness of attention modules to adver"},"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":"2110.13950","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-26T18:30:21Z","cross_cats_sorted":["cs.CR","cs.LG","cs.MM"],"title_canon_sha256":"11ca34d9b40d544e1c600d43a1ce15d5ae21ae053cbec271561ff239548da4ae","abstract_canon_sha256":"71cca7b711ca53c690ae1c5082031c904b0ac91566d62e5e5f9d91f67d4281f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:26:22.093008Z","signature_b64":"lRGG6NMlgZnYZY/ebjPOhsLCa6pPQZZuxLrIoOeiZss9UMGJ4XmcTDASB+p/vMGGfK+B5no8sguChNbvNM2GCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56390a8bcaada690f0681c29693e5ff89567da51c6c6a9184cb000c652974f96","last_reissued_at":"2026-07-05T03:26:22.092375Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:26:22.092375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can't Fool Me: Adversarially Robust Transformer for Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Divya Choudhary, Palash Goyal, Saurabh Sahu","submitted_at":"2021-10-26T18:30:21Z","abstract_excerpt":"Deep neural networks have been shown to perform poorly on adversarial examples. To address this, several techniques have been proposed to increase robustness of a model for image classification tasks. However, in video understanding tasks, developing adversarially robust models is still unexplored. In this paper, we aim to bridge this gap. We first show that simple extensions of image based adversarially robust models slightly improve the worst-case performance. Further, we propose a temporal attention regularization scheme in Transformer to improve the robustness of attention modules to adver"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.13950","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/2110.13950/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":"2110.13950","created_at":"2026-07-05T03:26:22.092466+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.13950v1","created_at":"2026-07-05T03:26:22.092466+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.13950","created_at":"2026-07-05T03:26:22.092466+00:00"},{"alias_kind":"pith_short_12","alias_value":"KY4QVC6KVWTJ","created_at":"2026-07-05T03:26:22.092466+00:00"},{"alias_kind":"pith_short_16","alias_value":"KY4QVC6KVWTJB4DI","created_at":"2026-07-05T03:26:22.092466+00:00"},{"alias_kind":"pith_short_8","alias_value":"KY4QVC6K","created_at":"2026-07-05T03:26:22.092466+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/KY4QVC6KVWTJB4DIDQUWSPS77C","json":"https://pith.science/pith/KY4QVC6KVWTJB4DIDQUWSPS77C.json","graph_json":"https://pith.science/api/pith-number/KY4QVC6KVWTJB4DIDQUWSPS77C/graph.json","events_json":"https://pith.science/api/pith-number/KY4QVC6KVWTJB4DIDQUWSPS77C/events.json","paper":"https://pith.science/paper/KY4QVC6K"},"agent_actions":{"view_html":"https://pith.science/pith/KY4QVC6KVWTJB4DIDQUWSPS77C","download_json":"https://pith.science/pith/KY4QVC6KVWTJB4DIDQUWSPS77C.json","view_paper":"https://pith.science/paper/KY4QVC6K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.13950&json=true","fetch_graph":"https://pith.science/api/pith-number/KY4QVC6KVWTJB4DIDQUWSPS77C/graph.json","fetch_events":"https://pith.science/api/pith-number/KY4QVC6KVWTJB4DIDQUWSPS77C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KY4QVC6KVWTJB4DIDQUWSPS77C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KY4QVC6KVWTJB4DIDQUWSPS77C/action/storage_attestation","attest_author":"https://pith.science/pith/KY4QVC6KVWTJB4DIDQUWSPS77C/action/author_attestation","sign_citation":"https://pith.science/pith/KY4QVC6KVWTJB4DIDQUWSPS77C/action/citation_signature","submit_replication":"https://pith.science/pith/KY4QVC6KVWTJB4DIDQUWSPS77C/action/replication_record"}},"created_at":"2026-07-05T03:26:22.092466+00:00","updated_at":"2026-07-05T03:26:22.092466+00:00"}