{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AXWLRE34DM76S5OMM2ZY6TQVUR","short_pith_number":"pith:AXWLRE34","schema_version":"1.0","canonical_sha256":"05ecb8937c1b3fe975cc66b38f4e15a45c8d1744deb5583afd80aaf049f64f46","source":{"kind":"arxiv","id":"2410.20019","version":1},"attestation_state":"computed","paper":{"title":"Attacks against Abstractive Text Summarization Models through Lead Bias and Influence Functions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.CL","authors_text":"Poojitha Thota, Shirin Nilizadeh","submitted_at":"2024-10-26T00:35:15Z","abstract_excerpt":"Large Language Models have introduced novel opportunities for text comprehension and generation. Yet, they are vulnerable to adversarial perturbations and data poisoning attacks, particularly in tasks like text classification and translation. However, the adversarial robustness of abstractive text summarization models remains less explored. In this work, we unveil a novel approach by exploiting the inherent lead bias in summarization models, to perform adversarial perturbations. Furthermore, we introduce an innovative application of influence functions, to execute data poisoning, which comprom"},"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":"2410.20019","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-26T00:35:15Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"6d21abbb12e12e741f53bb9f33eacb696a870efcb3d5201d0ce4d268a069182d","abstract_canon_sha256":"bceae89f51dc9fecea0b89ad8e371a1375f80b15792b647824b5013b093b1d80"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:26:37.622895Z","signature_b64":"hZfFDyasP/zLe9XwE/vx1qVsMZThan2fxEZ3BYD+Szf11TiptNxCqUHcm26BHXrOlYN/fUOvx/X6qOfPQ+6LBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05ecb8937c1b3fe975cc66b38f4e15a45c8d1744deb5583afd80aaf049f64f46","last_reissued_at":"2026-07-05T09:26:37.622347Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:26:37.622347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attacks against Abstractive Text Summarization Models through Lead Bias and Influence Functions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.CL","authors_text":"Poojitha Thota, Shirin Nilizadeh","submitted_at":"2024-10-26T00:35:15Z","abstract_excerpt":"Large Language Models have introduced novel opportunities for text comprehension and generation. Yet, they are vulnerable to adversarial perturbations and data poisoning attacks, particularly in tasks like text classification and translation. However, the adversarial robustness of abstractive text summarization models remains less explored. In this work, we unveil a novel approach by exploiting the inherent lead bias in summarization models, to perform adversarial perturbations. Furthermore, we introduce an innovative application of influence functions, to execute data poisoning, which comprom"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20019","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/2410.20019/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":"2410.20019","created_at":"2026-07-05T09:26:37.622413+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.20019v1","created_at":"2026-07-05T09:26:37.622413+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20019","created_at":"2026-07-05T09:26:37.622413+00:00"},{"alias_kind":"pith_short_12","alias_value":"AXWLRE34DM76","created_at":"2026-07-05T09:26:37.622413+00:00"},{"alias_kind":"pith_short_16","alias_value":"AXWLRE34DM76S5OM","created_at":"2026-07-05T09:26:37.622413+00:00"},{"alias_kind":"pith_short_8","alias_value":"AXWLRE34","created_at":"2026-07-05T09:26:37.622413+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/AXWLRE34DM76S5OMM2ZY6TQVUR","json":"https://pith.science/pith/AXWLRE34DM76S5OMM2ZY6TQVUR.json","graph_json":"https://pith.science/api/pith-number/AXWLRE34DM76S5OMM2ZY6TQVUR/graph.json","events_json":"https://pith.science/api/pith-number/AXWLRE34DM76S5OMM2ZY6TQVUR/events.json","paper":"https://pith.science/paper/AXWLRE34"},"agent_actions":{"view_html":"https://pith.science/pith/AXWLRE34DM76S5OMM2ZY6TQVUR","download_json":"https://pith.science/pith/AXWLRE34DM76S5OMM2ZY6TQVUR.json","view_paper":"https://pith.science/paper/AXWLRE34","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.20019&json=true","fetch_graph":"https://pith.science/api/pith-number/AXWLRE34DM76S5OMM2ZY6TQVUR/graph.json","fetch_events":"https://pith.science/api/pith-number/AXWLRE34DM76S5OMM2ZY6TQVUR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AXWLRE34DM76S5OMM2ZY6TQVUR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AXWLRE34DM76S5OMM2ZY6TQVUR/action/storage_attestation","attest_author":"https://pith.science/pith/AXWLRE34DM76S5OMM2ZY6TQVUR/action/author_attestation","sign_citation":"https://pith.science/pith/AXWLRE34DM76S5OMM2ZY6TQVUR/action/citation_signature","submit_replication":"https://pith.science/pith/AXWLRE34DM76S5OMM2ZY6TQVUR/action/replication_record"}},"created_at":"2026-07-05T09:26:37.622413+00:00","updated_at":"2026-07-05T09:26:37.622413+00:00"}