{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DVGT7MKPKF4EYSVLE57DKLMWVP","short_pith_number":"pith:DVGT7MKP","schema_version":"1.0","canonical_sha256":"1d4d3fb14f51784c4aab277e352d96abc6532e7586ecd7810f5392dc081d6d56","source":{"kind":"arxiv","id":"2402.03477","version":1},"attestation_state":"computed","paper":{"title":"Arabic Synonym BERT-based Adversarial Examples for Text Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Esma Wali, Jeanna Matthews, Norah Alshahrani, Saied Alshahrani","submitted_at":"2024-02-05T19:39:07Z","abstract_excerpt":"Text classification systems have been proven vulnerable to adversarial text examples, modified versions of the original text examples that are often unnoticed by human eyes, yet can force text classification models to alter their classification. Often, research works quantifying the impact of adversarial text attacks have been applied only to models trained in English. In this paper, we introduce the first word-level study of adversarial attacks in Arabic. Specifically, we use a synonym (word-level) attack using a Masked Language Modeling (MLM) task with a BERT model in a black-box setting to "},"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":"2402.03477","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-05T19:39:07Z","cross_cats_sorted":[],"title_canon_sha256":"c7ca1a04139a2c8a9dea11145bfa1c859830661bbfbca31f1c98d82ad601faa1","abstract_canon_sha256":"8be857301fccc4376ba268e3e8c053c6c497c49f42cc62cf1efe48a50fcb0fa1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:53.018228Z","signature_b64":"b9RFzgnhzqMt8NceTXB7fDsDZtMOZ1yU5tTFAuZkqqJgKiwfLmGfCePbwQClJkqKCX73RPwhe0da90HudN0uDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d4d3fb14f51784c4aab277e352d96abc6532e7586ecd7810f5392dc081d6d56","last_reissued_at":"2026-07-05T07:41:53.017817Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:53.017817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Arabic Synonym BERT-based Adversarial Examples for Text Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Esma Wali, Jeanna Matthews, Norah Alshahrani, Saied Alshahrani","submitted_at":"2024-02-05T19:39:07Z","abstract_excerpt":"Text classification systems have been proven vulnerable to adversarial text examples, modified versions of the original text examples that are often unnoticed by human eyes, yet can force text classification models to alter their classification. Often, research works quantifying the impact of adversarial text attacks have been applied only to models trained in English. In this paper, we introduce the first word-level study of adversarial attacks in Arabic. Specifically, we use a synonym (word-level) attack using a Masked Language Modeling (MLM) task with a BERT model in a black-box setting to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03477","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/2402.03477/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":"2402.03477","created_at":"2026-07-05T07:41:53.017876+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.03477v1","created_at":"2026-07-05T07:41:53.017876+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03477","created_at":"2026-07-05T07:41:53.017876+00:00"},{"alias_kind":"pith_short_12","alias_value":"DVGT7MKPKF4E","created_at":"2026-07-05T07:41:53.017876+00:00"},{"alias_kind":"pith_short_16","alias_value":"DVGT7MKPKF4EYSVL","created_at":"2026-07-05T07:41:53.017876+00:00"},{"alias_kind":"pith_short_8","alias_value":"DVGT7MKP","created_at":"2026-07-05T07:41:53.017876+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/DVGT7MKPKF4EYSVLE57DKLMWVP","json":"https://pith.science/pith/DVGT7MKPKF4EYSVLE57DKLMWVP.json","graph_json":"https://pith.science/api/pith-number/DVGT7MKPKF4EYSVLE57DKLMWVP/graph.json","events_json":"https://pith.science/api/pith-number/DVGT7MKPKF4EYSVLE57DKLMWVP/events.json","paper":"https://pith.science/paper/DVGT7MKP"},"agent_actions":{"view_html":"https://pith.science/pith/DVGT7MKPKF4EYSVLE57DKLMWVP","download_json":"https://pith.science/pith/DVGT7MKPKF4EYSVLE57DKLMWVP.json","view_paper":"https://pith.science/paper/DVGT7MKP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.03477&json=true","fetch_graph":"https://pith.science/api/pith-number/DVGT7MKPKF4EYSVLE57DKLMWVP/graph.json","fetch_events":"https://pith.science/api/pith-number/DVGT7MKPKF4EYSVLE57DKLMWVP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DVGT7MKPKF4EYSVLE57DKLMWVP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DVGT7MKPKF4EYSVLE57DKLMWVP/action/storage_attestation","attest_author":"https://pith.science/pith/DVGT7MKPKF4EYSVLE57DKLMWVP/action/author_attestation","sign_citation":"https://pith.science/pith/DVGT7MKPKF4EYSVLE57DKLMWVP/action/citation_signature","submit_replication":"https://pith.science/pith/DVGT7MKPKF4EYSVLE57DKLMWVP/action/replication_record"}},"created_at":"2026-07-05T07:41:53.017876+00:00","updated_at":"2026-07-05T07:41:53.017876+00:00"}