{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:M5QKE4EOQZANQFPDN7CY67NDIA","short_pith_number":"pith:M5QKE4EO","schema_version":"1.0","canonical_sha256":"6760a2708e8640d815e36fc58f7da3401ec3a9383174061f477ac373f9249e13","source":{"kind":"arxiv","id":"2309.11830","version":2},"attestation_state":"computed","paper":{"title":"Goal-Oriented Prompt Attack and Safety Evaluation for LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changlong Sun, Chengyuan Liu, Fei Wu, Fubang Zhao, Kun Kuang, Lizhi Qing, Yangyang Kang","submitted_at":"2023-09-21T07:07:49Z","abstract_excerpt":"Large Language Models (LLMs) presents significant priority in text understanding and generation. However, LLMs suffer from the risk of generating harmful contents especially while being employed to applications. There are several black-box attack methods, such as Prompt Attack, which can change the behaviour of LLMs and induce LLMs to generate unexpected answers with harmful contents. Researchers are interested in Prompt Attack and Defense with LLMs, while there is no publicly available dataset with high successful attacking rate to evaluate the abilities of defending prompt attack. In this pa"},"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":"2309.11830","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-21T07:07:49Z","cross_cats_sorted":[],"title_canon_sha256":"064b7c7f1c677c36e2e426cf287fef54eedc70e9d2c960539aaa1e89e2bf6cc2","abstract_canon_sha256":"9892521c7748e4336f94acfff53af183691b2dbc03ad7aa917c3fd09a182cfd7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:21:44.643931Z","signature_b64":"5rKd/+vHZ+yKNH2fRqudaFpSXFdz+gnzD9Vdc4AnxjOhyYSoKD+n7x+8CJ5w44EqH22QAhWzDO+qgtreV39xDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6760a2708e8640d815e36fc58f7da3401ec3a9383174061f477ac373f9249e13","last_reissued_at":"2026-07-05T07:21:44.643459Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:21:44.643459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Goal-Oriented Prompt Attack and Safety Evaluation for LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changlong Sun, Chengyuan Liu, Fei Wu, Fubang Zhao, Kun Kuang, Lizhi Qing, Yangyang Kang","submitted_at":"2023-09-21T07:07:49Z","abstract_excerpt":"Large Language Models (LLMs) presents significant priority in text understanding and generation. However, LLMs suffer from the risk of generating harmful contents especially while being employed to applications. There are several black-box attack methods, such as Prompt Attack, which can change the behaviour of LLMs and induce LLMs to generate unexpected answers with harmful contents. Researchers are interested in Prompt Attack and Defense with LLMs, while there is no publicly available dataset with high successful attacking rate to evaluate the abilities of defending prompt attack. In this pa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.11830","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/2309.11830/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":"2309.11830","created_at":"2026-07-05T07:21:44.643512+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.11830v2","created_at":"2026-07-05T07:21:44.643512+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.11830","created_at":"2026-07-05T07:21:44.643512+00:00"},{"alias_kind":"pith_short_12","alias_value":"M5QKE4EOQZAN","created_at":"2026-07-05T07:21:44.643512+00:00"},{"alias_kind":"pith_short_16","alias_value":"M5QKE4EOQZANQFPD","created_at":"2026-07-05T07:21:44.643512+00:00"},{"alias_kind":"pith_short_8","alias_value":"M5QKE4EO","created_at":"2026-07-05T07:21:44.643512+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.15594","citing_title":"A Survey on LLM-as-a-Judge","ref_index":92,"is_internal_anchor":false},{"citing_arxiv_id":"2407.04295","citing_title":"Jailbreak Attacks and Defenses Against Large Language Models: A Survey","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M5QKE4EOQZANQFPDN7CY67NDIA","json":"https://pith.science/pith/M5QKE4EOQZANQFPDN7CY67NDIA.json","graph_json":"https://pith.science/api/pith-number/M5QKE4EOQZANQFPDN7CY67NDIA/graph.json","events_json":"https://pith.science/api/pith-number/M5QKE4EOQZANQFPDN7CY67NDIA/events.json","paper":"https://pith.science/paper/M5QKE4EO"},"agent_actions":{"view_html":"https://pith.science/pith/M5QKE4EOQZANQFPDN7CY67NDIA","download_json":"https://pith.science/pith/M5QKE4EOQZANQFPDN7CY67NDIA.json","view_paper":"https://pith.science/paper/M5QKE4EO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.11830&json=true","fetch_graph":"https://pith.science/api/pith-number/M5QKE4EOQZANQFPDN7CY67NDIA/graph.json","fetch_events":"https://pith.science/api/pith-number/M5QKE4EOQZANQFPDN7CY67NDIA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M5QKE4EOQZANQFPDN7CY67NDIA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M5QKE4EOQZANQFPDN7CY67NDIA/action/storage_attestation","attest_author":"https://pith.science/pith/M5QKE4EOQZANQFPDN7CY67NDIA/action/author_attestation","sign_citation":"https://pith.science/pith/M5QKE4EOQZANQFPDN7CY67NDIA/action/citation_signature","submit_replication":"https://pith.science/pith/M5QKE4EOQZANQFPDN7CY67NDIA/action/replication_record"}},"created_at":"2026-07-05T07:21:44.643512+00:00","updated_at":"2026-07-05T07:21:44.643512+00:00"}