{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JP4XJRFCS4STEVVOIQKLMC7LCI","short_pith_number":"pith:JP4XJRFC","schema_version":"1.0","canonical_sha256":"4bf974c4a297253256ae4414b60beb123b74a3ab2fe200a17b8d49c21a9dfbc2","source":{"kind":"arxiv","id":"2311.09827","version":2},"attestation_state":"computed","paper":{"title":"Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bang Zheng Li, Ben Zhou, Chaowei Xiao, Fei Wang, Muhao Chen, Nan Xu","submitted_at":"2023-11-16T11:52:22Z","abstract_excerpt":"While large language models (LLMs) have demonstrated increasing power, they have also given rise to a wide range of harmful behaviors. As representatives, jailbreak attacks can provoke harmful or unethical responses from LLMs, even after safety alignment. In this paper, we investigate a novel category of jailbreak attacks specifically designed to target the cognitive structure and processes of LLMs. Specifically, we analyze the safety vulnerability of LLMs in the face of (1) multilingual cognitive overload, (2) veiled expression, and (3) effect-to-cause reasoning. Different from previous jailb"},"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":"2311.09827","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-16T11:52:22Z","cross_cats_sorted":[],"title_canon_sha256":"61536b88236e5688d9a2892b59f4435c3779256dec60d890afb89ac07b1f1e7d","abstract_canon_sha256":"c12990d338ce40d782f5e507827cfb0683287d769f69d3afe132c79e09fc73e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:21.614358Z","signature_b64":"XqoKSTGGrVBzbOHCoe05+qaY6yxCDOaZPGKIpvMijYCzr0+nSsiUI8U3hdZACmN1CFNfweK6ZlNwsqdQgMIUDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bf974c4a297253256ae4414b60beb123b74a3ab2fe200a17b8d49c21a9dfbc2","last_reissued_at":"2026-07-05T07:50:21.613839Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:21.613839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bang Zheng Li, Ben Zhou, Chaowei Xiao, Fei Wang, Muhao Chen, Nan Xu","submitted_at":"2023-11-16T11:52:22Z","abstract_excerpt":"While large language models (LLMs) have demonstrated increasing power, they have also given rise to a wide range of harmful behaviors. As representatives, jailbreak attacks can provoke harmful or unethical responses from LLMs, even after safety alignment. In this paper, we investigate a novel category of jailbreak attacks specifically designed to target the cognitive structure and processes of LLMs. Specifically, we analyze the safety vulnerability of LLMs in the face of (1) multilingual cognitive overload, (2) veiled expression, and (3) effect-to-cause reasoning. Different from previous jailb"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09827","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/2311.09827/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":"2311.09827","created_at":"2026-07-05T07:50:21.613904+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.09827v2","created_at":"2026-07-05T07:50:21.613904+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09827","created_at":"2026-07-05T07:50:21.613904+00:00"},{"alias_kind":"pith_short_12","alias_value":"JP4XJRFCS4ST","created_at":"2026-07-05T07:50:21.613904+00:00"},{"alias_kind":"pith_short_16","alias_value":"JP4XJRFCS4STEVVO","created_at":"2026-07-05T07:50:21.613904+00:00"},{"alias_kind":"pith_short_8","alias_value":"JP4XJRFC","created_at":"2026-07-05T07:50:21.613904+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.02356","citing_title":"ASTRA: An Automated Framework for Strategy Discovery, Retrieval, and Evolution for Jailbreaking LLMs","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2402.10260","citing_title":"A StrongREJECT for Empty Jailbreaks","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2406.11717","citing_title":"Refusal in Language Models Is Mediated by a Single Direction","ref_index":200,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JP4XJRFCS4STEVVOIQKLMC7LCI","json":"https://pith.science/pith/JP4XJRFCS4STEVVOIQKLMC7LCI.json","graph_json":"https://pith.science/api/pith-number/JP4XJRFCS4STEVVOIQKLMC7LCI/graph.json","events_json":"https://pith.science/api/pith-number/JP4XJRFCS4STEVVOIQKLMC7LCI/events.json","paper":"https://pith.science/paper/JP4XJRFC"},"agent_actions":{"view_html":"https://pith.science/pith/JP4XJRFCS4STEVVOIQKLMC7LCI","download_json":"https://pith.science/pith/JP4XJRFCS4STEVVOIQKLMC7LCI.json","view_paper":"https://pith.science/paper/JP4XJRFC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.09827&json=true","fetch_graph":"https://pith.science/api/pith-number/JP4XJRFCS4STEVVOIQKLMC7LCI/graph.json","fetch_events":"https://pith.science/api/pith-number/JP4XJRFCS4STEVVOIQKLMC7LCI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JP4XJRFCS4STEVVOIQKLMC7LCI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JP4XJRFCS4STEVVOIQKLMC7LCI/action/storage_attestation","attest_author":"https://pith.science/pith/JP4XJRFCS4STEVVOIQKLMC7LCI/action/author_attestation","sign_citation":"https://pith.science/pith/JP4XJRFCS4STEVVOIQKLMC7LCI/action/citation_signature","submit_replication":"https://pith.science/pith/JP4XJRFCS4STEVVOIQKLMC7LCI/action/replication_record"}},"created_at":"2026-07-05T07:50:21.613904+00:00","updated_at":"2026-07-05T07:50:21.613904+00:00"}