{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M5J7DLXXRP5BY7FPIQPCJW2KPB","short_pith_number":"pith:M5J7DLXX","schema_version":"1.0","canonical_sha256":"6753f1aef78bfa1c7caf441e24db4a7848483b5059d1e84dedb60cf3d4ec0d60","source":{"kind":"arxiv","id":"2412.17011","version":1},"attestation_state":"computed","paper":{"title":"Robustness of Large Language Models Against Adversarial Attacks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chuanqi Shi, Hang Zhang, Lun Wang, Shaoshuai Du, Yanxin Shen, Yixian Shen, Yiyi Tao","submitted_at":"2024-12-22T13:21:15Z","abstract_excerpt":"The increasing deployment of Large Language Models (LLMs) in various applications necessitates a rigorous evaluation of their robustness against adversarial attacks. In this paper, we present a comprehensive study on the robustness of GPT LLM family. We employ two distinct evaluation methods to assess their resilience. The first method introduce character-level text attack in input prompts, testing the models on three sentiment classification datasets: StanfordNLP/IMDB, Yelp Reviews, and SST-2. The second method involves using jailbreak prompts to challenge the safety mechanisms of the LLMs. O"},"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":"2412.17011","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-22T13:21:15Z","cross_cats_sorted":[],"title_canon_sha256":"dc52ebefa24241b8bc60aff50083a1400af42462fb4dd887e34effeb368f418c","abstract_canon_sha256":"134040ec10cc500b57e0bdfe38580a4e3c39c808d98303ef33e87f3344b34e16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:16.508931Z","signature_b64":"5A+wFehORHyuZZ/4OAkcxrDrZCRdSGq2I4CQ+s8Vix2kEIDb4ZY4ORNmjZQdWZIU1SIrPejxZL1npURuB6fLDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6753f1aef78bfa1c7caf441e24db4a7848483b5059d1e84dedb60cf3d4ec0d60","last_reissued_at":"2026-07-05T09:53:16.508377Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:16.508377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robustness of Large Language Models Against Adversarial Attacks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chuanqi Shi, Hang Zhang, Lun Wang, Shaoshuai Du, Yanxin Shen, Yixian Shen, Yiyi Tao","submitted_at":"2024-12-22T13:21:15Z","abstract_excerpt":"The increasing deployment of Large Language Models (LLMs) in various applications necessitates a rigorous evaluation of their robustness against adversarial attacks. In this paper, we present a comprehensive study on the robustness of GPT LLM family. We employ two distinct evaluation methods to assess their resilience. The first method introduce character-level text attack in input prompts, testing the models on three sentiment classification datasets: StanfordNLP/IMDB, Yelp Reviews, and SST-2. The second method involves using jailbreak prompts to challenge the safety mechanisms of the LLMs. O"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17011","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/2412.17011/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":"2412.17011","created_at":"2026-07-05T09:53:16.508439+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.17011v1","created_at":"2026-07-05T09:53:16.508439+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17011","created_at":"2026-07-05T09:53:16.508439+00:00"},{"alias_kind":"pith_short_12","alias_value":"M5J7DLXXRP5B","created_at":"2026-07-05T09:53:16.508439+00:00"},{"alias_kind":"pith_short_16","alias_value":"M5J7DLXXRP5BY7FP","created_at":"2026-07-05T09:53:16.508439+00:00"},{"alias_kind":"pith_short_8","alias_value":"M5J7DLXX","created_at":"2026-07-05T09:53:16.508439+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/M5J7DLXXRP5BY7FPIQPCJW2KPB","json":"https://pith.science/pith/M5J7DLXXRP5BY7FPIQPCJW2KPB.json","graph_json":"https://pith.science/api/pith-number/M5J7DLXXRP5BY7FPIQPCJW2KPB/graph.json","events_json":"https://pith.science/api/pith-number/M5J7DLXXRP5BY7FPIQPCJW2KPB/events.json","paper":"https://pith.science/paper/M5J7DLXX"},"agent_actions":{"view_html":"https://pith.science/pith/M5J7DLXXRP5BY7FPIQPCJW2KPB","download_json":"https://pith.science/pith/M5J7DLXXRP5BY7FPIQPCJW2KPB.json","view_paper":"https://pith.science/paper/M5J7DLXX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.17011&json=true","fetch_graph":"https://pith.science/api/pith-number/M5J7DLXXRP5BY7FPIQPCJW2KPB/graph.json","fetch_events":"https://pith.science/api/pith-number/M5J7DLXXRP5BY7FPIQPCJW2KPB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M5J7DLXXRP5BY7FPIQPCJW2KPB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M5J7DLXXRP5BY7FPIQPCJW2KPB/action/storage_attestation","attest_author":"https://pith.science/pith/M5J7DLXXRP5BY7FPIQPCJW2KPB/action/author_attestation","sign_citation":"https://pith.science/pith/M5J7DLXXRP5BY7FPIQPCJW2KPB/action/citation_signature","submit_replication":"https://pith.science/pith/M5J7DLXXRP5BY7FPIQPCJW2KPB/action/replication_record"}},"created_at":"2026-07-05T09:53:16.508439+00:00","updated_at":"2026-07-05T09:53:16.508439+00:00"}