{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:XXU3DEDJW6TX4PPU66KCFRX4KM","short_pith_number":"pith:XXU3DEDJ","schema_version":"1.0","canonical_sha256":"bde9b19069b7a77e3df4f79422c6fc5317e8a4b18aa01c27c481354372fd3642","source":{"kind":"arxiv","id":"2111.05468","version":1},"attestation_state":"computed","paper":{"title":"Sparse Adversarial Video Attacks with Spatial Transformations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Leandro Soriano Marcolino, Qiang Ni, Ronghui Mu, Wenjie Ruan","submitted_at":"2021-11-10T00:37:35Z","abstract_excerpt":"In recent years, a significant amount of research efforts concentrated on adversarial attacks on images, while adversarial video attacks have seldom been explored. We propose an adversarial attack strategy on videos, called DeepSAVA. Our model includes both additive perturbation and spatial transformation by a unified optimisation framework, where the structural similarity index (SSIM) measure is adopted to measure the adversarial distance. We design an effective and novel optimisation scheme which alternatively utilizes Bayesian optimisation to identify the most influential frame in a video a"},"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":"2111.05468","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-10T00:37:35Z","cross_cats_sorted":[],"title_canon_sha256":"ba477a8d8e1bc2eabf0343ad628d6b4372e914c16079cf7f17ffe37bc3a025f2","abstract_canon_sha256":"ce965c8b8c66866df3ec845581ae685138220bddf73237155dc7d24e997c2985"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:30:44.668365Z","signature_b64":"ieMEHogcCqZNZcMDB+/C0vZARO8zA+PGUNoD9H8PgvdSrLoFLJtX1fNgf3kezRDMgvNw5MKlM49wdALd/cakCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bde9b19069b7a77e3df4f79422c6fc5317e8a4b18aa01c27c481354372fd3642","last_reissued_at":"2026-07-05T03:30:44.667883Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:30:44.667883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sparse Adversarial Video Attacks with Spatial Transformations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Leandro Soriano Marcolino, Qiang Ni, Ronghui Mu, Wenjie Ruan","submitted_at":"2021-11-10T00:37:35Z","abstract_excerpt":"In recent years, a significant amount of research efforts concentrated on adversarial attacks on images, while adversarial video attacks have seldom been explored. We propose an adversarial attack strategy on videos, called DeepSAVA. Our model includes both additive perturbation and spatial transformation by a unified optimisation framework, where the structural similarity index (SSIM) measure is adopted to measure the adversarial distance. We design an effective and novel optimisation scheme which alternatively utilizes Bayesian optimisation to identify the most influential frame in a video a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.05468","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/2111.05468/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":"2111.05468","created_at":"2026-07-05T03:30:44.667940+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.05468v1","created_at":"2026-07-05T03:30:44.667940+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.05468","created_at":"2026-07-05T03:30:44.667940+00:00"},{"alias_kind":"pith_short_12","alias_value":"XXU3DEDJW6TX","created_at":"2026-07-05T03:30:44.667940+00:00"},{"alias_kind":"pith_short_16","alias_value":"XXU3DEDJW6TX4PPU","created_at":"2026-07-05T03:30:44.667940+00:00"},{"alias_kind":"pith_short_8","alias_value":"XXU3DEDJ","created_at":"2026-07-05T03:30:44.667940+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15416","citing_title":"Margin-Adaptive Confidence Ranking for Reliable LLM Judgement","ref_index":261,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XXU3DEDJW6TX4PPU66KCFRX4KM","json":"https://pith.science/pith/XXU3DEDJW6TX4PPU66KCFRX4KM.json","graph_json":"https://pith.science/api/pith-number/XXU3DEDJW6TX4PPU66KCFRX4KM/graph.json","events_json":"https://pith.science/api/pith-number/XXU3DEDJW6TX4PPU66KCFRX4KM/events.json","paper":"https://pith.science/paper/XXU3DEDJ"},"agent_actions":{"view_html":"https://pith.science/pith/XXU3DEDJW6TX4PPU66KCFRX4KM","download_json":"https://pith.science/pith/XXU3DEDJW6TX4PPU66KCFRX4KM.json","view_paper":"https://pith.science/paper/XXU3DEDJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.05468&json=true","fetch_graph":"https://pith.science/api/pith-number/XXU3DEDJW6TX4PPU66KCFRX4KM/graph.json","fetch_events":"https://pith.science/api/pith-number/XXU3DEDJW6TX4PPU66KCFRX4KM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XXU3DEDJW6TX4PPU66KCFRX4KM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XXU3DEDJW6TX4PPU66KCFRX4KM/action/storage_attestation","attest_author":"https://pith.science/pith/XXU3DEDJW6TX4PPU66KCFRX4KM/action/author_attestation","sign_citation":"https://pith.science/pith/XXU3DEDJW6TX4PPU66KCFRX4KM/action/citation_signature","submit_replication":"https://pith.science/pith/XXU3DEDJW6TX4PPU66KCFRX4KM/action/replication_record"}},"created_at":"2026-07-05T03:30:44.667940+00:00","updated_at":"2026-07-05T03:30:44.667940+00:00"}