{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DJIRP3HOWCTE5C7TGC7T54FWVM","short_pith_number":"pith:DJIRP3HO","schema_version":"1.0","canonical_sha256":"1a5117eceeb0a64e8bf330bf3ef0b6ab2f5b3b03089e62fe61798d817283da03","source":{"kind":"arxiv","id":"2607.27373","version":1},"attestation_state":"computed","paper":{"title":"RoguePrompt: Dual-Layer Encoding for Self-Reconstruction to Circumvent LLM Moderation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Benyamin Tafreshian, Prathamesh Dhake","submitted_at":"2026-07-29T18:25:30Z","abstract_excerpt":"Large language models (LLMs) are becoming increasingly integrated into mainstream development platforms and daily technological workflows, typically behind moderation and safety controls. Despite these controls, preventing prompt-based policy evasion remains challenging, and adversaries continue to \"jailbreak\" LLMs by crafting prompts that circumvent implemented safety mechanisms. Prior work has established cipher-mediated interaction, code-embedded decryption, prompt decomposition and reconstruction, and layered custom encryption as viable attack primitives. However, reported evaluations gene"},"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":"2607.27373","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-07-29T18:25:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e214a4ddd208e86eea655fccb462e24df4808bdb6e17c8285b5e171f3bdd2983","abstract_canon_sha256":"93ce59c527475f9fb1db05049487f8c4922a0b1716efbf41ea31b99888fc6727"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a5117eceeb0a64e8bf330bf3ef0b6ab2f5b3b03089e62fe61798d817283da03","last_reissued_at":"2026-07-31T00:10:47.936851Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T00:10:47.936851Z"},"graph_snapshot":{"paper":{"title":"RoguePrompt: Dual-Layer Encoding for Self-Reconstruction to Circumvent LLM Moderation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Benyamin Tafreshian, Prathamesh Dhake","submitted_at":"2026-07-29T18:25:30Z","abstract_excerpt":"Large language models (LLMs) are becoming increasingly integrated into mainstream development platforms and daily technological workflows, typically behind moderation and safety controls. Despite these controls, preventing prompt-based policy evasion remains challenging, and adversaries continue to \"jailbreak\" LLMs by crafting prompts that circumvent implemented safety mechanisms. Prior work has established cipher-mediated interaction, code-embedded decryption, prompt decomposition and reconstruction, and layered custom encryption as viable attack primitives. However, reported evaluations gene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27373","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/2607.27373/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":"2607.27373","created_at":"2026-07-31T00:10:47.939309+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.27373v1","created_at":"2026-07-31T00:10:47.939309+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27373","created_at":"2026-07-31T00:10:47.939309+00:00"},{"alias_kind":"pith_short_12","alias_value":"DJIRP3HOWCTE","created_at":"2026-07-31T00:10:47.939309+00:00"},{"alias_kind":"pith_short_16","alias_value":"DJIRP3HOWCTE5C7T","created_at":"2026-07-31T00:10:47.939309+00:00"},{"alias_kind":"pith_short_8","alias_value":"DJIRP3HO","created_at":"2026-07-31T00:10:47.939309+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/DJIRP3HOWCTE5C7TGC7T54FWVM","json":"https://pith.science/pith/DJIRP3HOWCTE5C7TGC7T54FWVM.json","graph_json":"https://pith.science/api/pith-number/DJIRP3HOWCTE5C7TGC7T54FWVM/graph.json","events_json":"https://pith.science/api/pith-number/DJIRP3HOWCTE5C7TGC7T54FWVM/events.json","paper":"https://pith.science/paper/DJIRP3HO"},"agent_actions":{"view_html":"https://pith.science/pith/DJIRP3HOWCTE5C7TGC7T54FWVM","download_json":"https://pith.science/pith/DJIRP3HOWCTE5C7TGC7T54FWVM.json","view_paper":"https://pith.science/paper/DJIRP3HO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.27373&json=true","fetch_graph":"https://pith.science/api/pith-number/DJIRP3HOWCTE5C7TGC7T54FWVM/graph.json","fetch_events":"https://pith.science/api/pith-number/DJIRP3HOWCTE5C7TGC7T54FWVM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DJIRP3HOWCTE5C7TGC7T54FWVM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DJIRP3HOWCTE5C7TGC7T54FWVM/action/storage_attestation","attest_author":"https://pith.science/pith/DJIRP3HOWCTE5C7TGC7T54FWVM/action/author_attestation","sign_citation":"https://pith.science/pith/DJIRP3HOWCTE5C7TGC7T54FWVM/action/citation_signature","submit_replication":"https://pith.science/pith/DJIRP3HOWCTE5C7TGC7T54FWVM/action/replication_record"}},"created_at":"2026-07-31T00:10:47.939309+00:00","updated_at":"2026-07-31T00:10:47.939309+00:00"}