{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:UTMHYKGDJARDKGP74IF3ZAJIFK","short_pith_number":"pith:UTMHYKGD","schema_version":"1.0","canonical_sha256":"a4d87c28c348223519ffe20bbc81282a84ddf6ad17eebbc680234cd804a68877","source":{"kind":"arxiv","id":"2010.13773","version":1},"attestation_state":"computed","paper":{"title":"GreedyFool: Distortion-Aware Sparse Adversarial Attack","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuan Qin, Dong Chen, Dongdong Chen, Jianmin Bao, Lu Yuan, Nenghai Yu, Weiming Zhang, Xiaoyi Dong","submitted_at":"2020-10-26T17:59:07Z","abstract_excerpt":"Modern deep neural networks(DNNs) are vulnerable to adversarial samples. Sparse adversarial samples are a special branch of adversarial samples that can fool the target model by only perturbing a few pixels. The existence of the sparse adversarial attack points out that DNNs are much more vulnerable than people believed, which is also a new aspect for analyzing DNNs. However, current sparse adversarial attack methods still have some shortcomings on both sparsity and invisibility. In this paper, we propose a novel two-stage distortion-aware greedy-based method dubbed as \"GreedyFool\". Specifical"},"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":"2010.13773","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-10-26T17:59:07Z","cross_cats_sorted":[],"title_canon_sha256":"25e4dd011458df460d210c39957fc37925ce786c85359d700294135785f2c652","abstract_canon_sha256":"46f68448a03c222508f2cdba5c64a8620f99dfec836819ddad3fbe167a5d6890"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:47:10.150478Z","signature_b64":"hl0+YqPiFgq6r4aKtuF4E4o56X2JD4M/arBtbXiFnbxWMdBe1DzXZoTM5pfSrkEppOnbZ+NV1a7wJSkyON0WBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4d87c28c348223519ffe20bbc81282a84ddf6ad17eebbc680234cd804a68877","last_reissued_at":"2026-07-05T01:47:10.150055Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:47:10.150055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GreedyFool: Distortion-Aware Sparse Adversarial Attack","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuan Qin, Dong Chen, Dongdong Chen, Jianmin Bao, Lu Yuan, Nenghai Yu, Weiming Zhang, Xiaoyi Dong","submitted_at":"2020-10-26T17:59:07Z","abstract_excerpt":"Modern deep neural networks(DNNs) are vulnerable to adversarial samples. Sparse adversarial samples are a special branch of adversarial samples that can fool the target model by only perturbing a few pixels. The existence of the sparse adversarial attack points out that DNNs are much more vulnerable than people believed, which is also a new aspect for analyzing DNNs. However, current sparse adversarial attack methods still have some shortcomings on both sparsity and invisibility. In this paper, we propose a novel two-stage distortion-aware greedy-based method dubbed as \"GreedyFool\". Specifical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.13773","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/2010.13773/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":"2010.13773","created_at":"2026-07-05T01:47:10.150114+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.13773v1","created_at":"2026-07-05T01:47:10.150114+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.13773","created_at":"2026-07-05T01:47:10.150114+00:00"},{"alias_kind":"pith_short_12","alias_value":"UTMHYKGDJARD","created_at":"2026-07-05T01:47:10.150114+00:00"},{"alias_kind":"pith_short_16","alias_value":"UTMHYKGDJARDKGP7","created_at":"2026-07-05T01:47:10.150114+00:00"},{"alias_kind":"pith_short_8","alias_value":"UTMHYKGD","created_at":"2026-07-05T01:47:10.150114+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.04057","citing_title":"LaPrune: Controllable Differentiable Sparsity at Million Scale","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UTMHYKGDJARDKGP74IF3ZAJIFK","json":"https://pith.science/pith/UTMHYKGDJARDKGP74IF3ZAJIFK.json","graph_json":"https://pith.science/api/pith-number/UTMHYKGDJARDKGP74IF3ZAJIFK/graph.json","events_json":"https://pith.science/api/pith-number/UTMHYKGDJARDKGP74IF3ZAJIFK/events.json","paper":"https://pith.science/paper/UTMHYKGD"},"agent_actions":{"view_html":"https://pith.science/pith/UTMHYKGDJARDKGP74IF3ZAJIFK","download_json":"https://pith.science/pith/UTMHYKGDJARDKGP74IF3ZAJIFK.json","view_paper":"https://pith.science/paper/UTMHYKGD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.13773&json=true","fetch_graph":"https://pith.science/api/pith-number/UTMHYKGDJARDKGP74IF3ZAJIFK/graph.json","fetch_events":"https://pith.science/api/pith-number/UTMHYKGDJARDKGP74IF3ZAJIFK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UTMHYKGDJARDKGP74IF3ZAJIFK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UTMHYKGDJARDKGP74IF3ZAJIFK/action/storage_attestation","attest_author":"https://pith.science/pith/UTMHYKGDJARDKGP74IF3ZAJIFK/action/author_attestation","sign_citation":"https://pith.science/pith/UTMHYKGDJARDKGP74IF3ZAJIFK/action/citation_signature","submit_replication":"https://pith.science/pith/UTMHYKGDJARDKGP74IF3ZAJIFK/action/replication_record"}},"created_at":"2026-07-05T01:47:10.150114+00:00","updated_at":"2026-07-05T01:47:10.150114+00:00"}