{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZA5NJW4UGSSEWNKWA3VPL36QJK","short_pith_number":"pith:ZA5NJW4U","schema_version":"1.0","canonical_sha256":"c83ad4db9434a44b355606eaf5efd04aa06e59b54d6f212780f35de34671c3a9","source":{"kind":"arxiv","id":"2503.00416","version":1},"attestation_state":"computed","paper":{"title":"Breaking the Loop: Detecting and Mitigating Denial-of-Service Vulnerabilities in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.PF"],"primary_cat":"cs.CR","authors_text":"Huijia Sun, Junzhe Yu, Ling Shi, Yi Liu, Yuqi Chen","submitted_at":"2025-03-01T09:32:17Z","abstract_excerpt":"Large Language Models (LLMs) have significantly advanced text understanding and generation, becoming integral to applications across education, software development, healthcare, entertainment, and legal services. Despite considerable progress in improving model reliability, latency remains under-explored, particularly through recurrent generation, where models repeatedly produce similar or identical outputs, causing increased latency and potential Denial-of-Service (DoS) vulnerabilities.\n  We propose RecurrentGenerator, a black-box evolutionary algorithm that efficiently identifies recurrent g"},"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":"2503.00416","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-03-01T09:32:17Z","cross_cats_sorted":["cs.AI","cs.PF"],"title_canon_sha256":"8cffc41b8b60ccec702a20c511c686975850d8701f1bc069f072f752252b138e","abstract_canon_sha256":"69af72622ecd29f7627a70fe7a411475c57cfda7737348e13d43be9c56606531"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:22.468803Z","signature_b64":"SxnuoO4EZkLcA0GPLdyXhSHHwdbs9QuvpsPXpsGEeT3ZH+1rDYwfGgQJCADkusgMGp6pCxFJA3Asz/2zz6fTDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c83ad4db9434a44b355606eaf5efd04aa06e59b54d6f212780f35de34671c3a9","last_reissued_at":"2026-07-05T10:22:22.468329Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:22.468329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Breaking the Loop: Detecting and Mitigating Denial-of-Service Vulnerabilities in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.PF"],"primary_cat":"cs.CR","authors_text":"Huijia Sun, Junzhe Yu, Ling Shi, Yi Liu, Yuqi Chen","submitted_at":"2025-03-01T09:32:17Z","abstract_excerpt":"Large Language Models (LLMs) have significantly advanced text understanding and generation, becoming integral to applications across education, software development, healthcare, entertainment, and legal services. Despite considerable progress in improving model reliability, latency remains under-explored, particularly through recurrent generation, where models repeatedly produce similar or identical outputs, causing increased latency and potential Denial-of-Service (DoS) vulnerabilities.\n  We propose RecurrentGenerator, a black-box evolutionary algorithm that efficiently identifies recurrent g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00416","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/2503.00416/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":"2503.00416","created_at":"2026-07-05T10:22:22.468391+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.00416v1","created_at":"2026-07-05T10:22:22.468391+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00416","created_at":"2026-07-05T10:22:22.468391+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZA5NJW4UGSSE","created_at":"2026-07-05T10:22:22.468391+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZA5NJW4UGSSEWNKW","created_at":"2026-07-05T10:22:22.468391+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZA5NJW4U","created_at":"2026-07-05T10:22:22.468391+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.16068","citing_title":"Resource Consumption Threats in Large Language Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11442","citing_title":"Can a Single Message Paralyze the AI Infrastructure? The Rise of AbO-DDoS Attacks through Targeted Mobius Injection","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZA5NJW4UGSSEWNKWA3VPL36QJK","json":"https://pith.science/pith/ZA5NJW4UGSSEWNKWA3VPL36QJK.json","graph_json":"https://pith.science/api/pith-number/ZA5NJW4UGSSEWNKWA3VPL36QJK/graph.json","events_json":"https://pith.science/api/pith-number/ZA5NJW4UGSSEWNKWA3VPL36QJK/events.json","paper":"https://pith.science/paper/ZA5NJW4U"},"agent_actions":{"view_html":"https://pith.science/pith/ZA5NJW4UGSSEWNKWA3VPL36QJK","download_json":"https://pith.science/pith/ZA5NJW4UGSSEWNKWA3VPL36QJK.json","view_paper":"https://pith.science/paper/ZA5NJW4U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.00416&json=true","fetch_graph":"https://pith.science/api/pith-number/ZA5NJW4UGSSEWNKWA3VPL36QJK/graph.json","fetch_events":"https://pith.science/api/pith-number/ZA5NJW4UGSSEWNKWA3VPL36QJK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZA5NJW4UGSSEWNKWA3VPL36QJK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZA5NJW4UGSSEWNKWA3VPL36QJK/action/storage_attestation","attest_author":"https://pith.science/pith/ZA5NJW4UGSSEWNKWA3VPL36QJK/action/author_attestation","sign_citation":"https://pith.science/pith/ZA5NJW4UGSSEWNKWA3VPL36QJK/action/citation_signature","submit_replication":"https://pith.science/pith/ZA5NJW4UGSSEWNKWA3VPL36QJK/action/replication_record"}},"created_at":"2026-07-05T10:22:22.468391+00:00","updated_at":"2026-07-05T10:22:22.468391+00:00"}