{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:JPDJIEYGYUF3FGVX6XURYDYGTQ","short_pith_number":"pith:JPDJIEYG","schema_version":"1.0","canonical_sha256":"4bc6941306c50bb29ab7f5e91c0f069c381d7df7026f0991bcab80b5b115ed11","source":{"kind":"arxiv","id":"2107.04284","version":2},"attestation_state":"computed","paper":{"title":"Universal 3-Dimensional Perturbations for Black-Box Attacks on Video Recognition Systems","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Han Wang, Shangyu Xie, Yuan Hong, Yu Kong","submitted_at":"2021-07-09T07:55:21Z","abstract_excerpt":"Widely deployed deep neural network (DNN) models have been proven to be vulnerable to adversarial perturbations in many applications (e.g., image, audio and text classifications). To date, there are only a few adversarial perturbations proposed to deviate the DNN models in video recognition systems by simply injecting 2D perturbations into video frames. However, such attacks may overly perturb the videos without learning the spatio-temporal features (across temporal frames), which are commonly extracted by DNN models for video recognition. To our best knowledge, we propose the first black-box "},"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":"2107.04284","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CR","submitted_at":"2021-07-09T07:55:21Z","cross_cats_sorted":[],"title_canon_sha256":"5a5cfcda6bd83ed2198aa22771de02c488fdc342ce368095f6be835d9236304a","abstract_canon_sha256":"5b433e0c2e95869ab7c2a09345e7d3af4c7baa02ec1cb1fe645262be27eababa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:05:51.946211Z","signature_b64":"HzzVs3+M4BHx+47hS2df3E0YvG3N51bCZTTfdDMseXkLV4hEUOLDCBB5UHmaRBrXlex5sUaY6KXR3OjhzkK/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bc6941306c50bb29ab7f5e91c0f069c381d7df7026f0991bcab80b5b115ed11","last_reissued_at":"2026-07-05T03:05:51.945668Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:05:51.945668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Universal 3-Dimensional Perturbations for Black-Box Attacks on Video Recognition Systems","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Han Wang, Shangyu Xie, Yuan Hong, Yu Kong","submitted_at":"2021-07-09T07:55:21Z","abstract_excerpt":"Widely deployed deep neural network (DNN) models have been proven to be vulnerable to adversarial perturbations in many applications (e.g., image, audio and text classifications). To date, there are only a few adversarial perturbations proposed to deviate the DNN models in video recognition systems by simply injecting 2D perturbations into video frames. However, such attacks may overly perturb the videos without learning the spatio-temporal features (across temporal frames), which are commonly extracted by DNN models for video recognition. To our best knowledge, we propose the first black-box "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.04284","kind":"arxiv","version":2},"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/2107.04284/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":"2107.04284","created_at":"2026-07-05T03:05:51.945728+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.04284v2","created_at":"2026-07-05T03:05:51.945728+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.04284","created_at":"2026-07-05T03:05:51.945728+00:00"},{"alias_kind":"pith_short_12","alias_value":"JPDJIEYGYUF3","created_at":"2026-07-05T03:05:51.945728+00:00"},{"alias_kind":"pith_short_16","alias_value":"JPDJIEYGYUF3FGVX","created_at":"2026-07-05T03:05:51.945728+00:00"},{"alias_kind":"pith_short_8","alias_value":"JPDJIEYG","created_at":"2026-07-05T03:05:51.945728+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/JPDJIEYGYUF3FGVX6XURYDYGTQ","json":"https://pith.science/pith/JPDJIEYGYUF3FGVX6XURYDYGTQ.json","graph_json":"https://pith.science/api/pith-number/JPDJIEYGYUF3FGVX6XURYDYGTQ/graph.json","events_json":"https://pith.science/api/pith-number/JPDJIEYGYUF3FGVX6XURYDYGTQ/events.json","paper":"https://pith.science/paper/JPDJIEYG"},"agent_actions":{"view_html":"https://pith.science/pith/JPDJIEYGYUF3FGVX6XURYDYGTQ","download_json":"https://pith.science/pith/JPDJIEYGYUF3FGVX6XURYDYGTQ.json","view_paper":"https://pith.science/paper/JPDJIEYG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.04284&json=true","fetch_graph":"https://pith.science/api/pith-number/JPDJIEYGYUF3FGVX6XURYDYGTQ/graph.json","fetch_events":"https://pith.science/api/pith-number/JPDJIEYGYUF3FGVX6XURYDYGTQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JPDJIEYGYUF3FGVX6XURYDYGTQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JPDJIEYGYUF3FGVX6XURYDYGTQ/action/storage_attestation","attest_author":"https://pith.science/pith/JPDJIEYGYUF3FGVX6XURYDYGTQ/action/author_attestation","sign_citation":"https://pith.science/pith/JPDJIEYGYUF3FGVX6XURYDYGTQ/action/citation_signature","submit_replication":"https://pith.science/pith/JPDJIEYGYUF3FGVX6XURYDYGTQ/action/replication_record"}},"created_at":"2026-07-05T03:05:51.945728+00:00","updated_at":"2026-07-05T03:05:51.945728+00:00"}