{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TXYMQZHBPPALQ7Q7W26OPOT2X6","short_pith_number":"pith:TXYMQZHB","schema_version":"1.0","canonical_sha256":"9df0c864e17bc0b87e1fb6bce7ba7abf86bc3e3e2fa441451b58182f7e16075c","source":{"kind":"arxiv","id":"2506.22557","version":2},"attestation_state":"computed","paper":{"title":"MetaCipher: A Time-Persistent and Universal Multi-Agent Framework for Cipher-Based Jailbreak Attacks for LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Abdul Basit, Boyuan Chen, Minghao Shao, Muhammad Shafique, Siddharth Garg","submitted_at":"2025-06-27T18:15:56Z","abstract_excerpt":"As large language models (LLMs) grow more capable, they face growing vulnerability to sophisticated jailbreak attacks. While developers invest heavily in alignment finetuning and safety guardrails, researchers continue publishing novel attacks, driving progress through adversarial iteration. This dynamic mirrors a strategic game of continual evolution. However, two major challenges hinder jailbreak development: the high cost of querying top-tier LLMs and the short lifespan of effective attacks due to frequent safety updates. These factors limit cost-efficiency and practical impact of research "},"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":"2506.22557","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-06-27T18:15:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"41338a6f8a6030d15e04c76f8373b8338446201b9eaca9b02ea686549b0c8b0d","abstract_canon_sha256":"c42ae60cbf35a38678b997a375147462f02504bfd2fb51104f7f518459860fc6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:04.813249Z","signature_b64":"YSvHv/UIVLKqcr5947Fo+qgLXoe+rYIkAkFVynYGZy278J7MTuth8iTKgUveyADse+fzMuBrQgCHtkp7dC2bDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9df0c864e17bc0b87e1fb6bce7ba7abf86bc3e3e2fa441451b58182f7e16075c","last_reissued_at":"2026-07-05T11:53:04.812804Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:04.812804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MetaCipher: A Time-Persistent and Universal Multi-Agent Framework for Cipher-Based Jailbreak Attacks for LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Abdul Basit, Boyuan Chen, Minghao Shao, Muhammad Shafique, Siddharth Garg","submitted_at":"2025-06-27T18:15:56Z","abstract_excerpt":"As large language models (LLMs) grow more capable, they face growing vulnerability to sophisticated jailbreak attacks. While developers invest heavily in alignment finetuning and safety guardrails, researchers continue publishing novel attacks, driving progress through adversarial iteration. This dynamic mirrors a strategic game of continual evolution. However, two major challenges hinder jailbreak development: the high cost of querying top-tier LLMs and the short lifespan of effective attacks due to frequent safety updates. These factors limit cost-efficiency and practical impact of research "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22557","kind":"arxiv","version":2},"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/2506.22557/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":"2506.22557","created_at":"2026-07-05T11:53:04.812861+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.22557v2","created_at":"2026-07-05T11:53:04.812861+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22557","created_at":"2026-07-05T11:53:04.812861+00:00"},{"alias_kind":"pith_short_12","alias_value":"TXYMQZHBPPAL","created_at":"2026-07-05T11:53:04.812861+00:00"},{"alias_kind":"pith_short_16","alias_value":"TXYMQZHBPPALQ7Q7","created_at":"2026-07-05T11:53:04.812861+00:00"},{"alias_kind":"pith_short_8","alias_value":"TXYMQZHB","created_at":"2026-07-05T11:53:04.812861+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29237","citing_title":"Evolving Skill-Structured Attack Memory Enhances LLM Jailbreaking","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17948","citing_title":"RAVEN: Retrieval-Augmented Vulnerability Exploration Network for Memory Corruption Analysis in User Code and Binary Programs","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17093","citing_title":"HarmChip: Evaluating Hardware Security Centric LLM Safety via Jailbreak Benchmarking","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TXYMQZHBPPALQ7Q7W26OPOT2X6","json":"https://pith.science/pith/TXYMQZHBPPALQ7Q7W26OPOT2X6.json","graph_json":"https://pith.science/api/pith-number/TXYMQZHBPPALQ7Q7W26OPOT2X6/graph.json","events_json":"https://pith.science/api/pith-number/TXYMQZHBPPALQ7Q7W26OPOT2X6/events.json","paper":"https://pith.science/paper/TXYMQZHB"},"agent_actions":{"view_html":"https://pith.science/pith/TXYMQZHBPPALQ7Q7W26OPOT2X6","download_json":"https://pith.science/pith/TXYMQZHBPPALQ7Q7W26OPOT2X6.json","view_paper":"https://pith.science/paper/TXYMQZHB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.22557&json=true","fetch_graph":"https://pith.science/api/pith-number/TXYMQZHBPPALQ7Q7W26OPOT2X6/graph.json","fetch_events":"https://pith.science/api/pith-number/TXYMQZHBPPALQ7Q7W26OPOT2X6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TXYMQZHBPPALQ7Q7W26OPOT2X6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TXYMQZHBPPALQ7Q7W26OPOT2X6/action/storage_attestation","attest_author":"https://pith.science/pith/TXYMQZHBPPALQ7Q7W26OPOT2X6/action/author_attestation","sign_citation":"https://pith.science/pith/TXYMQZHBPPALQ7Q7W26OPOT2X6/action/citation_signature","submit_replication":"https://pith.science/pith/TXYMQZHBPPALQ7Q7W26OPOT2X6/action/replication_record"}},"created_at":"2026-07-05T11:53:04.812861+00:00","updated_at":"2026-07-05T11:53:04.812861+00:00"}