{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4PFU3XB5C4X3FJ4OQ346765FCX","short_pith_number":"pith:4PFU3XB5","schema_version":"1.0","canonical_sha256":"e3cb4ddc3d172fb2a78e86f9effba515c65ba22d73ff0bdf8cd0b38d93745101","source":{"kind":"arxiv","id":"2507.05288","version":1},"attestation_state":"computed","paper":{"title":"A Survey on Proactive Defense Strategies Against Misinformation in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Aiwei Liu, Bingchen Duan, He Geng, Hongyi Liu, Jia Liu, Peijie Jiang, Qi Zheng, Shuliang Liu, Xuming Hu, Yibo Yan","submitted_at":"2025-07-05T09:52:21Z","abstract_excerpt":"The widespread deployment of large language models (LLMs) across critical domains has amplified the societal risks posed by algorithmically generated misinformation. Unlike traditional false content, LLM-generated misinformation can be self-reinforcing, highly plausible, and capable of rapid propagation across multiple languages, which traditional detection methods fail to mitigate effectively. This paper introduces a proactive defense paradigm, shifting from passive post hoc detection to anticipatory mitigation strategies. We propose a Three Pillars framework: (1) Knowledge Credibility, forti"},"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":"2507.05288","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-05T09:52:21Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"cf6570f696627fed0c223a703c80b1ef3ce30e4098a4543fe6b09b2ff0968263","abstract_canon_sha256":"12b5e3a5644ec4a672dae2187fb4020601c75de3fcf308e86b9bf43d50f739f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:27.642068Z","signature_b64":"VMiEyvZ5MBijFZjaUBvuKL6qOxZjFO7KSEg56XRlA6ztxl5LZLVeIhsFXMLQDkWX/wrY1mdsB0Hi+GijfQ+fDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3cb4ddc3d172fb2a78e86f9effba515c65ba22d73ff0bdf8cd0b38d93745101","last_reissued_at":"2026-07-05T11:33:27.641574Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:27.641574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Proactive Defense Strategies Against Misinformation in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Aiwei Liu, Bingchen Duan, He Geng, Hongyi Liu, Jia Liu, Peijie Jiang, Qi Zheng, Shuliang Liu, Xuming Hu, Yibo Yan","submitted_at":"2025-07-05T09:52:21Z","abstract_excerpt":"The widespread deployment of large language models (LLMs) across critical domains has amplified the societal risks posed by algorithmically generated misinformation. Unlike traditional false content, LLM-generated misinformation can be self-reinforcing, highly plausible, and capable of rapid propagation across multiple languages, which traditional detection methods fail to mitigate effectively. This paper introduces a proactive defense paradigm, shifting from passive post hoc detection to anticipatory mitigation strategies. We propose a Three Pillars framework: (1) Knowledge Credibility, forti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05288","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/2507.05288/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":"2507.05288","created_at":"2026-07-05T11:33:27.641632+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.05288v1","created_at":"2026-07-05T11:33:27.641632+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05288","created_at":"2026-07-05T11:33:27.641632+00:00"},{"alias_kind":"pith_short_12","alias_value":"4PFU3XB5C4X3","created_at":"2026-07-05T11:33:27.641632+00:00"},{"alias_kind":"pith_short_16","alias_value":"4PFU3XB5C4X3FJ4O","created_at":"2026-07-05T11:33:27.641632+00:00"},{"alias_kind":"pith_short_8","alias_value":"4PFU3XB5","created_at":"2026-07-05T11:33:27.641632+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.12424","citing_title":"Decoding by Perturbation: Mitigating MLLM Hallucinations via Dynamic Textual Perturbation","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4PFU3XB5C4X3FJ4OQ346765FCX","json":"https://pith.science/pith/4PFU3XB5C4X3FJ4OQ346765FCX.json","graph_json":"https://pith.science/api/pith-number/4PFU3XB5C4X3FJ4OQ346765FCX/graph.json","events_json":"https://pith.science/api/pith-number/4PFU3XB5C4X3FJ4OQ346765FCX/events.json","paper":"https://pith.science/paper/4PFU3XB5"},"agent_actions":{"view_html":"https://pith.science/pith/4PFU3XB5C4X3FJ4OQ346765FCX","download_json":"https://pith.science/pith/4PFU3XB5C4X3FJ4OQ346765FCX.json","view_paper":"https://pith.science/paper/4PFU3XB5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.05288&json=true","fetch_graph":"https://pith.science/api/pith-number/4PFU3XB5C4X3FJ4OQ346765FCX/graph.json","fetch_events":"https://pith.science/api/pith-number/4PFU3XB5C4X3FJ4OQ346765FCX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4PFU3XB5C4X3FJ4OQ346765FCX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4PFU3XB5C4X3FJ4OQ346765FCX/action/storage_attestation","attest_author":"https://pith.science/pith/4PFU3XB5C4X3FJ4OQ346765FCX/action/author_attestation","sign_citation":"https://pith.science/pith/4PFU3XB5C4X3FJ4OQ346765FCX/action/citation_signature","submit_replication":"https://pith.science/pith/4PFU3XB5C4X3FJ4OQ346765FCX/action/replication_record"}},"created_at":"2026-07-05T11:33:27.641632+00:00","updated_at":"2026-07-05T11:33:27.641632+00:00"}