{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:X5FAIRKSFA4UR6LRHLSIZP566S","short_pith_number":"pith:X5FAIRKS","schema_version":"1.0","canonical_sha256":"bf4a044552283948f9713ae48cbfbef48b45b891d560d31dfab18f8e09c9163a","source":{"kind":"arxiv","id":"1807.03326","version":3},"attestation_state":"computed","paper":{"title":"Adaptive Adversarial Attack on Scene Text Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dapeng Oliver Wu, Pan He, Xiaolin Andy Li, Xiaoyong Yuan","submitted_at":"2018-07-09T18:12:27Z","abstract_excerpt":"Recent studies have shown that state-of-the-art deep learning models are vulnerable to the inputs with small perturbations (adversarial examples). We observe two critical obstacles in adversarial examples: (i) Strong adversarial attacks (e.g., C&W attack) require manually tuning hyper-parameters and take a long time to construct an adversarial example, making it impractical to attack real-time systems; (ii) Most of the studies focus on non-sequential tasks, such as image classification, yet only a few consider sequential tasks. In this work, we speed up adversarial attacks, especially on seque"},"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":"1807.03326","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-09T18:12:27Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"b0373a48f0955cb2219accd491b1b4d00bbb017463229d3478aec8461bdab9d0","abstract_canon_sha256":"b75acf5748f8ae0dfaa8ecf54050fa4a7ac2bad84528d6eacb6cb70e0d8147c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:52:05.429621Z","signature_b64":"BiA4Jud2GDNwJnUJC5aj6MwJdNNUht8hcutADnCtp1ZG9ePC9+zLjR22DUtDbKuUBlhigb2krWpbk4tcto1TDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf4a044552283948f9713ae48cbfbef48b45b891d560d31dfab18f8e09c9163a","last_reissued_at":"2026-07-05T00:52:05.429244Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:52:05.429244Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Adversarial Attack on Scene Text Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dapeng Oliver Wu, Pan He, Xiaolin Andy Li, Xiaoyong Yuan","submitted_at":"2018-07-09T18:12:27Z","abstract_excerpt":"Recent studies have shown that state-of-the-art deep learning models are vulnerable to the inputs with small perturbations (adversarial examples). We observe two critical obstacles in adversarial examples: (i) Strong adversarial attacks (e.g., C&W attack) require manually tuning hyper-parameters and take a long time to construct an adversarial example, making it impractical to attack real-time systems; (ii) Most of the studies focus on non-sequential tasks, such as image classification, yet only a few consider sequential tasks. In this work, we speed up adversarial attacks, especially on seque"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.03326","kind":"arxiv","version":3},"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/1807.03326/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":"1807.03326","created_at":"2026-07-05T00:52:05.429300+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.03326v3","created_at":"2026-07-05T00:52:05.429300+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.03326","created_at":"2026-07-05T00:52:05.429300+00:00"},{"alias_kind":"pith_short_12","alias_value":"X5FAIRKSFA4U","created_at":"2026-07-05T00:52:05.429300+00:00"},{"alias_kind":"pith_short_16","alias_value":"X5FAIRKSFA4UR6LR","created_at":"2026-07-05T00:52:05.429300+00:00"},{"alias_kind":"pith_short_8","alias_value":"X5FAIRKS","created_at":"2026-07-05T00:52:05.429300+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.00706","citing_title":"AdvGAN++ : Harnessing latent layers for adversary generation","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X5FAIRKSFA4UR6LRHLSIZP566S","json":"https://pith.science/pith/X5FAIRKSFA4UR6LRHLSIZP566S.json","graph_json":"https://pith.science/api/pith-number/X5FAIRKSFA4UR6LRHLSIZP566S/graph.json","events_json":"https://pith.science/api/pith-number/X5FAIRKSFA4UR6LRHLSIZP566S/events.json","paper":"https://pith.science/paper/X5FAIRKS"},"agent_actions":{"view_html":"https://pith.science/pith/X5FAIRKSFA4UR6LRHLSIZP566S","download_json":"https://pith.science/pith/X5FAIRKSFA4UR6LRHLSIZP566S.json","view_paper":"https://pith.science/paper/X5FAIRKS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.03326&json=true","fetch_graph":"https://pith.science/api/pith-number/X5FAIRKSFA4UR6LRHLSIZP566S/graph.json","fetch_events":"https://pith.science/api/pith-number/X5FAIRKSFA4UR6LRHLSIZP566S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X5FAIRKSFA4UR6LRHLSIZP566S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X5FAIRKSFA4UR6LRHLSIZP566S/action/storage_attestation","attest_author":"https://pith.science/pith/X5FAIRKSFA4UR6LRHLSIZP566S/action/author_attestation","sign_citation":"https://pith.science/pith/X5FAIRKSFA4UR6LRHLSIZP566S/action/citation_signature","submit_replication":"https://pith.science/pith/X5FAIRKSFA4UR6LRHLSIZP566S/action/replication_record"}},"created_at":"2026-07-05T00:52:05.429300+00:00","updated_at":"2026-07-05T00:52:05.429300+00:00"}