{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IEAS4CI2QVA3MTB35MJSLJKEXC","short_pith_number":"pith:IEAS4CI2","schema_version":"1.0","canonical_sha256":"41012e091a8541b64c3beb1325a544b8807c7bd5dd03b197dde460aec081b807","source":{"kind":"arxiv","id":"2210.09364","version":3},"attestation_state":"computed","paper":{"title":"Probabilistic Categorical Adversarial Attack & Adversarial Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Han Xu, Hui Liu, Jie Ren, Jiliang Tang, Pengfei He, Yuxuan Wan, Zitao Liu","submitted_at":"2022-10-17T19:04:16Z","abstract_excerpt":"The existence of adversarial examples brings huge concern for people to apply Deep Neural Networks (DNNs) in safety-critical tasks. However, how to generate adversarial examples with categorical data is an important problem but lack of extensive exploration. Previously established methods leverage greedy search method, which can be very time-consuming to conduct successful attack. This also limits the development of adversarial training and potential defenses for categorical data. To tackle this problem, we propose Probabilistic Categorical Adversarial Attack (PCAA), which transfers the discre"},"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":"2210.09364","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-17T19:04:16Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"49ed73dfa111dd316e0905200dfba4b17ca280e9f13bc763f76b7f96e8257a2d","abstract_canon_sha256":"0d242baa4ee95e30b80d6a582979d65d2732cddaa3d89a32783df18b0d42a5e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:09:44.045609Z","signature_b64":"3Xjqe4UnZa8NOX8sQQiBdB5R2S9aRus7vxIT306h5K9wz5gCLu8xJg8dJMysL1ecQ6ziXe0j4IdR15VdiwLpDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41012e091a8541b64c3beb1325a544b8807c7bd5dd03b197dde460aec081b807","last_reissued_at":"2026-07-05T07:09:44.044979Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:09:44.044979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Probabilistic Categorical Adversarial Attack & Adversarial Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Han Xu, Hui Liu, Jie Ren, Jiliang Tang, Pengfei He, Yuxuan Wan, Zitao Liu","submitted_at":"2022-10-17T19:04:16Z","abstract_excerpt":"The existence of adversarial examples brings huge concern for people to apply Deep Neural Networks (DNNs) in safety-critical tasks. However, how to generate adversarial examples with categorical data is an important problem but lack of extensive exploration. Previously established methods leverage greedy search method, which can be very time-consuming to conduct successful attack. This also limits the development of adversarial training and potential defenses for categorical data. To tackle this problem, we propose Probabilistic Categorical Adversarial Attack (PCAA), which transfers the discre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.09364","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/2210.09364/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":"2210.09364","created_at":"2026-07-05T07:09:44.045076+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.09364v3","created_at":"2026-07-05T07:09:44.045076+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.09364","created_at":"2026-07-05T07:09:44.045076+00:00"},{"alias_kind":"pith_short_12","alias_value":"IEAS4CI2QVA3","created_at":"2026-07-05T07:09:44.045076+00:00"},{"alias_kind":"pith_short_16","alias_value":"IEAS4CI2QVA3MTB3","created_at":"2026-07-05T07:09:44.045076+00:00"},{"alias_kind":"pith_short_8","alias_value":"IEAS4CI2","created_at":"2026-07-05T07:09:44.045076+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/IEAS4CI2QVA3MTB35MJSLJKEXC","json":"https://pith.science/pith/IEAS4CI2QVA3MTB35MJSLJKEXC.json","graph_json":"https://pith.science/api/pith-number/IEAS4CI2QVA3MTB35MJSLJKEXC/graph.json","events_json":"https://pith.science/api/pith-number/IEAS4CI2QVA3MTB35MJSLJKEXC/events.json","paper":"https://pith.science/paper/IEAS4CI2"},"agent_actions":{"view_html":"https://pith.science/pith/IEAS4CI2QVA3MTB35MJSLJKEXC","download_json":"https://pith.science/pith/IEAS4CI2QVA3MTB35MJSLJKEXC.json","view_paper":"https://pith.science/paper/IEAS4CI2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.09364&json=true","fetch_graph":"https://pith.science/api/pith-number/IEAS4CI2QVA3MTB35MJSLJKEXC/graph.json","fetch_events":"https://pith.science/api/pith-number/IEAS4CI2QVA3MTB35MJSLJKEXC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IEAS4CI2QVA3MTB35MJSLJKEXC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IEAS4CI2QVA3MTB35MJSLJKEXC/action/storage_attestation","attest_author":"https://pith.science/pith/IEAS4CI2QVA3MTB35MJSLJKEXC/action/author_attestation","sign_citation":"https://pith.science/pith/IEAS4CI2QVA3MTB35MJSLJKEXC/action/citation_signature","submit_replication":"https://pith.science/pith/IEAS4CI2QVA3MTB35MJSLJKEXC/action/replication_record"}},"created_at":"2026-07-05T07:09:44.045076+00:00","updated_at":"2026-07-05T07:09:44.045076+00:00"}