{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FWSYTUPDIDL5YERYXALZBG6QJN","short_pith_number":"pith:FWSYTUPD","schema_version":"1.0","canonical_sha256":"2da589d1e340d7dc1238b817909bd04b40fa6d04db95f8cccbe59a36eae04e66","source":{"kind":"arxiv","id":"2310.09652","version":1},"attestation_state":"computed","paper":{"title":"BufferSearch: Generating Black-Box Adversarial Texts With Lower Queries","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Qi Xuan, Tianyi Chen, Wenjie Lv, Yitao Zheng, Zhehua Zhong, Zhen Wang","submitted_at":"2023-10-14T19:49:02Z","abstract_excerpt":"Machine learning security has recently become a prominent topic in the natural language processing (NLP) area. The existing black-box adversarial attack suffers prohibitively from the high model querying complexity, resulting in easily being captured by anti-attack monitors. Meanwhile, how to eliminate redundant model queries is rarely explored. In this paper, we propose a query-efficient approach BufferSearch to effectively attack general intelligent NLP systems with the minimal number of querying requests. In general, BufferSearch makes use of historical information and conducts statistical "},"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":"2310.09652","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2023-10-14T19:49:02Z","cross_cats_sorted":[],"title_canon_sha256":"e0c5d9b9f5a7d663ff1af3e5117ed87f4ef91d2922f08e7ed61911e18b135401","abstract_canon_sha256":"bb39d2a268ab6fafac62dd7e35b64e1cecc9c5a48a52003a3544925ab25d2d8a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:09.188056Z","signature_b64":"uSohsLV7F5//JnK0BuK9/gxgsxjGXB6wkqRSD6gbUe72qetAXUVjsRKTojCfUV14+kPOBethn4rRzoGEEuGhDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2da589d1e340d7dc1238b817909bd04b40fa6d04db95f8cccbe59a36eae04e66","last_reissued_at":"2026-07-05T07:01:09.187594Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:09.187594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BufferSearch: Generating Black-Box Adversarial Texts With Lower Queries","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Qi Xuan, Tianyi Chen, Wenjie Lv, Yitao Zheng, Zhehua Zhong, Zhen Wang","submitted_at":"2023-10-14T19:49:02Z","abstract_excerpt":"Machine learning security has recently become a prominent topic in the natural language processing (NLP) area. The existing black-box adversarial attack suffers prohibitively from the high model querying complexity, resulting in easily being captured by anti-attack monitors. Meanwhile, how to eliminate redundant model queries is rarely explored. In this paper, we propose a query-efficient approach BufferSearch to effectively attack general intelligent NLP systems with the minimal number of querying requests. In general, BufferSearch makes use of historical information and conducts statistical "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.09652","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/2310.09652/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":"2310.09652","created_at":"2026-07-05T07:01:09.187648+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.09652v1","created_at":"2026-07-05T07:01:09.187648+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.09652","created_at":"2026-07-05T07:01:09.187648+00:00"},{"alias_kind":"pith_short_12","alias_value":"FWSYTUPDIDL5","created_at":"2026-07-05T07:01:09.187648+00:00"},{"alias_kind":"pith_short_16","alias_value":"FWSYTUPDIDL5YERY","created_at":"2026-07-05T07:01:09.187648+00:00"},{"alias_kind":"pith_short_8","alias_value":"FWSYTUPD","created_at":"2026-07-05T07:01:09.187648+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/FWSYTUPDIDL5YERYXALZBG6QJN","json":"https://pith.science/pith/FWSYTUPDIDL5YERYXALZBG6QJN.json","graph_json":"https://pith.science/api/pith-number/FWSYTUPDIDL5YERYXALZBG6QJN/graph.json","events_json":"https://pith.science/api/pith-number/FWSYTUPDIDL5YERYXALZBG6QJN/events.json","paper":"https://pith.science/paper/FWSYTUPD"},"agent_actions":{"view_html":"https://pith.science/pith/FWSYTUPDIDL5YERYXALZBG6QJN","download_json":"https://pith.science/pith/FWSYTUPDIDL5YERYXALZBG6QJN.json","view_paper":"https://pith.science/paper/FWSYTUPD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.09652&json=true","fetch_graph":"https://pith.science/api/pith-number/FWSYTUPDIDL5YERYXALZBG6QJN/graph.json","fetch_events":"https://pith.science/api/pith-number/FWSYTUPDIDL5YERYXALZBG6QJN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FWSYTUPDIDL5YERYXALZBG6QJN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FWSYTUPDIDL5YERYXALZBG6QJN/action/storage_attestation","attest_author":"https://pith.science/pith/FWSYTUPDIDL5YERYXALZBG6QJN/action/author_attestation","sign_citation":"https://pith.science/pith/FWSYTUPDIDL5YERYXALZBG6QJN/action/citation_signature","submit_replication":"https://pith.science/pith/FWSYTUPDIDL5YERYXALZBG6QJN/action/replication_record"}},"created_at":"2026-07-05T07:01:09.187648+00:00","updated_at":"2026-07-05T07:01:09.187648+00:00"}