{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VWRHULXZJVPZAIYGTBEL6XGAUT","short_pith_number":"pith:VWRHULXZ","schema_version":"1.0","canonical_sha256":"ada27a2ef94d5f9023069848bf5cc0a4c6d55ff73c361f26fb772ae5362a707c","source":{"kind":"arxiv","id":"2405.14023","version":1},"attestation_state":"computed","paper":{"title":"WordGame: Efficient & Effective LLM Jailbreak via Simultaneous Obfuscation in Query and Response","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bochuan Cao, Jinghui Chen, Lu Lin, Prasenjit Mitra, Tianrong Zhang, Yuanpu Cao","submitted_at":"2024-05-22T21:59:22Z","abstract_excerpt":"The recent breakthrough in large language models (LLMs) such as ChatGPT has revolutionized production processes at an unprecedented pace. Alongside this progress also comes mounting concerns about LLMs' susceptibility to jailbreaking attacks, which leads to the generation of harmful or unsafe content. While safety alignment measures have been implemented in LLMs to mitigate existing jailbreak attempts and force them to become increasingly complicated, it is still far from perfect. In this paper, we analyze the common pattern of the current safety alignment and show that it is possible to explo"},"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":"2405.14023","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-22T21:59:22Z","cross_cats_sorted":[],"title_canon_sha256":"5693d0feeb498583d054490380d3e5cdd1a99a419ab09f3b5666317cf37447b1","abstract_canon_sha256":"98c4de8847c9bf91badea2fc7ec5b1ec71d4e7a21c023badf9aa6fb07d3818f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:09.430782Z","signature_b64":"AMUbM724DsIsJeadpEupPQW+ZYabKcAeMwOpxSB1n2zpj65eCsNbFge6uYTaIugAeu//kM2sWF3tu7I0xcJODQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ada27a2ef94d5f9023069848bf5cc0a4c6d55ff73c361f26fb772ae5362a707c","last_reissued_at":"2026-07-05T08:22:09.430395Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:09.430395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WordGame: Efficient & Effective LLM Jailbreak via Simultaneous Obfuscation in Query and Response","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bochuan Cao, Jinghui Chen, Lu Lin, Prasenjit Mitra, Tianrong Zhang, Yuanpu Cao","submitted_at":"2024-05-22T21:59:22Z","abstract_excerpt":"The recent breakthrough in large language models (LLMs) such as ChatGPT has revolutionized production processes at an unprecedented pace. Alongside this progress also comes mounting concerns about LLMs' susceptibility to jailbreaking attacks, which leads to the generation of harmful or unsafe content. While safety alignment measures have been implemented in LLMs to mitigate existing jailbreak attempts and force them to become increasingly complicated, it is still far from perfect. In this paper, we analyze the common pattern of the current safety alignment and show that it is possible to explo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14023","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/2405.14023/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":"2405.14023","created_at":"2026-07-05T08:22:09.430450+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.14023v1","created_at":"2026-07-05T08:22:09.430450+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14023","created_at":"2026-07-05T08:22:09.430450+00:00"},{"alias_kind":"pith_short_12","alias_value":"VWRHULXZJVPZ","created_at":"2026-07-05T08:22:09.430450+00:00"},{"alias_kind":"pith_short_16","alias_value":"VWRHULXZJVPZAIYG","created_at":"2026-07-05T08:22:09.430450+00:00"},{"alias_kind":"pith_short_8","alias_value":"VWRHULXZ","created_at":"2026-07-05T08:22:09.430450+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/VWRHULXZJVPZAIYGTBEL6XGAUT","json":"https://pith.science/pith/VWRHULXZJVPZAIYGTBEL6XGAUT.json","graph_json":"https://pith.science/api/pith-number/VWRHULXZJVPZAIYGTBEL6XGAUT/graph.json","events_json":"https://pith.science/api/pith-number/VWRHULXZJVPZAIYGTBEL6XGAUT/events.json","paper":"https://pith.science/paper/VWRHULXZ"},"agent_actions":{"view_html":"https://pith.science/pith/VWRHULXZJVPZAIYGTBEL6XGAUT","download_json":"https://pith.science/pith/VWRHULXZJVPZAIYGTBEL6XGAUT.json","view_paper":"https://pith.science/paper/VWRHULXZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.14023&json=true","fetch_graph":"https://pith.science/api/pith-number/VWRHULXZJVPZAIYGTBEL6XGAUT/graph.json","fetch_events":"https://pith.science/api/pith-number/VWRHULXZJVPZAIYGTBEL6XGAUT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VWRHULXZJVPZAIYGTBEL6XGAUT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VWRHULXZJVPZAIYGTBEL6XGAUT/action/storage_attestation","attest_author":"https://pith.science/pith/VWRHULXZJVPZAIYGTBEL6XGAUT/action/author_attestation","sign_citation":"https://pith.science/pith/VWRHULXZJVPZAIYGTBEL6XGAUT/action/citation_signature","submit_replication":"https://pith.science/pith/VWRHULXZJVPZAIYGTBEL6XGAUT/action/replication_record"}},"created_at":"2026-07-05T08:22:09.430450+00:00","updated_at":"2026-07-05T08:22:09.430450+00:00"}