{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:A2JZXNIKJ4EXD5WNXQK5XP6SMQ","short_pith_number":"pith:A2JZXNIK","schema_version":"1.0","canonical_sha256":"06939bb50a4f0971f6cdbc15dbbfd26425dd10d186344db10c3dba757486497f","source":{"kind":"arxiv","id":"2505.16263","version":1},"attestation_state":"computed","paper":{"title":"All You Need is \"Leet\": Evading Hate-speech Detection AI","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CR","authors_text":"Naman Ahuja, Sampanna Yashwant Kahu","submitted_at":"2025-05-22T05:55:26Z","abstract_excerpt":"Social media and online forums are increasingly becoming popular. Unfortunately, these platforms are being used for spreading hate speech. In this paper, we design black-box techniques to protect users from hate-speech on online platforms by generating perturbations that can fool state of the art deep learning based hate speech detection models thereby decreasing their efficiency. We also ensure a minimal change in the original meaning of hate-speech. Our best perturbation attack is successfully able to evade hate-speech detection for 86.8 % of hateful text."},"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":"2505.16263","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CR","submitted_at":"2025-05-22T05:55:26Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"0534e493ed450fe11e67c35f80598ecbdd470c844c6cc3bd1cc10aee82460923","abstract_canon_sha256":"2b42a6ba57fafa822621c18f2d18aa410dea5383710291c757cfb85eaa4d7b59"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:32.362984Z","signature_b64":"6pRsWInGIcYB84Aoq7voMIZMWYwd6f46fK4rS8vN5INGvOlIXgD3Qgeg9J933fpPETsBM0OxzQ6OvoRNKRV8CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06939bb50a4f0971f6cdbc15dbbfd26425dd10d186344db10c3dba757486497f","last_reissued_at":"2026-07-05T11:07:32.362573Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:32.362573Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"All You Need is \"Leet\": Evading Hate-speech Detection AI","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CR","authors_text":"Naman Ahuja, Sampanna Yashwant Kahu","submitted_at":"2025-05-22T05:55:26Z","abstract_excerpt":"Social media and online forums are increasingly becoming popular. Unfortunately, these platforms are being used for spreading hate speech. In this paper, we design black-box techniques to protect users from hate-speech on online platforms by generating perturbations that can fool state of the art deep learning based hate speech detection models thereby decreasing their efficiency. We also ensure a minimal change in the original meaning of hate-speech. Our best perturbation attack is successfully able to evade hate-speech detection for 86.8 % of hateful text."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16263","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/2505.16263/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":"2505.16263","created_at":"2026-07-05T11:07:32.362644+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.16263v1","created_at":"2026-07-05T11:07:32.362644+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16263","created_at":"2026-07-05T11:07:32.362644+00:00"},{"alias_kind":"pith_short_12","alias_value":"A2JZXNIKJ4EX","created_at":"2026-07-05T11:07:32.362644+00:00"},{"alias_kind":"pith_short_16","alias_value":"A2JZXNIKJ4EXD5WN","created_at":"2026-07-05T11:07:32.362644+00:00"},{"alias_kind":"pith_short_8","alias_value":"A2JZXNIK","created_at":"2026-07-05T11:07:32.362644+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/A2JZXNIKJ4EXD5WNXQK5XP6SMQ","json":"https://pith.science/pith/A2JZXNIKJ4EXD5WNXQK5XP6SMQ.json","graph_json":"https://pith.science/api/pith-number/A2JZXNIKJ4EXD5WNXQK5XP6SMQ/graph.json","events_json":"https://pith.science/api/pith-number/A2JZXNIKJ4EXD5WNXQK5XP6SMQ/events.json","paper":"https://pith.science/paper/A2JZXNIK"},"agent_actions":{"view_html":"https://pith.science/pith/A2JZXNIKJ4EXD5WNXQK5XP6SMQ","download_json":"https://pith.science/pith/A2JZXNIKJ4EXD5WNXQK5XP6SMQ.json","view_paper":"https://pith.science/paper/A2JZXNIK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.16263&json=true","fetch_graph":"https://pith.science/api/pith-number/A2JZXNIKJ4EXD5WNXQK5XP6SMQ/graph.json","fetch_events":"https://pith.science/api/pith-number/A2JZXNIKJ4EXD5WNXQK5XP6SMQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A2JZXNIKJ4EXD5WNXQK5XP6SMQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A2JZXNIKJ4EXD5WNXQK5XP6SMQ/action/storage_attestation","attest_author":"https://pith.science/pith/A2JZXNIKJ4EXD5WNXQK5XP6SMQ/action/author_attestation","sign_citation":"https://pith.science/pith/A2JZXNIKJ4EXD5WNXQK5XP6SMQ/action/citation_signature","submit_replication":"https://pith.science/pith/A2JZXNIKJ4EXD5WNXQK5XP6SMQ/action/replication_record"}},"created_at":"2026-07-05T11:07:32.362644+00:00","updated_at":"2026-07-05T11:07:32.362644+00:00"}