{"id":"https://openalex.org/W7166803349","doi":"https://doi.org/10.18653/v1/2026.acl-long.2100","title":"SHARP: Self-adaptive Harmful Category-aware Prompt Generation for Black-box Jailbreaking","display_name":"SHARP: Self-adaptive Harmful Category-aware Prompt Generation for Black-box Jailbreaking","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166803349","doi":"https://doi.org/10.18653/v1/2026.acl-long.2100"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.2100","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2100","pdf_url":"https://aclanthology.org/2026.acl-long.2100.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.2100.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031912520","display_name":"Yingjie Xue","orcid":"https://orcid.org/0000-0003-1421-5427"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yingjie Xue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139820774","display_name":"Xingyou Xia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xingyou Xia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139834593","display_name":"Jun Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011542448","display_name":"Yunbo Cao","orcid":"https://orcid.org/0009-0005-2558-5206"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunbo Cao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050526815","display_name":"Dengpan Ye","orcid":"https://orcid.org/0000-0003-2510-9523"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dengpan Ye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070742322","display_name":"Guotong Geng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guotong Geng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139749854","display_name":"Fei Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fei Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.7928503,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"45291","last_page":"45303"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.3864000141620636,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.3864000141620636,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.21080000698566437,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12034","display_name":"Digital and Cyber Forensics","score":0.05480000004172325,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.21150000393390656},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.195700004696846},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.19519999623298645}],"concepts":[{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.258899986743927},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2418999969959259},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.21369999647140503},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.21150000393390656},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.195700004696846},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.19519999623298645},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.19519999623298645},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.18860000371932983},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.18400000035762787},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.1768999993801117}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.2100","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2100","pdf_url":"https://aclanthology.org/2026.acl-long.2100.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.2100","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2100","pdf_url":"https://aclanthology.org/2026.acl-long.2100.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2134083184","display_name":null,"funder_award_id":"No. 62472325","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5626719751","display_name":null,"funder_award_id":"62472325","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8963342785","display_name":null,"funder_award_id":"2025ZD0123603","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166803349.pdf","grobid_xml":"https://content.openalex.org/works/W7166803349.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"been":[5],"widely":[6],"applied":[7],"in":[8,24],"various":[9],"domains":[10],"such":[11],"as":[12],"education":[13],"and":[14,29,54,91,104,113,124,138],"healthcare,":[15],"making":[16],"safety":[17,97],"assurance":[18],"crucial.Jailbreak":[19],"attacks,":[20],"a":[21,78],"method":[22,99],"used":[23],"red-teaming,":[25],"can":[26],"help":[27],"evaluate":[28],"improve":[30],"the":[31,41,60,68,84,131],"defensive":[32],"strategies":[33],"of":[34,46,71],"LLMs.However,":[35],"existing":[36],"jailbreak":[37,63,80],"methods":[38],"often":[39],"overlook":[40],"semantic":[42,69,89],"differences":[43],"across":[44],"categories":[45],"harmful":[47,72],"questions,":[48],"leading":[49],"to":[50,86,108,130],"inconsistent":[51],"success":[52,112,122],"rates":[53,123],"reduced":[55],"overall":[56],"attack":[57,111,121],"effectiveness.We":[58],"propose":[59],"first":[61],"category-aware":[62],"framework,":[64],"SHARP,":[65],"which":[66],"incorporates":[67],"category":[70,114],"questions":[73],"into":[74],"prompt":[75],"generation.Trained":[76],"on":[77],"verified":[79],"dataset,":[81],"SHARP":[82,118],"enables":[83],"model":[85],"learn":[87],"category-specific":[88],"features":[90],"adaptively":[92],"generate":[93],"prompts":[94],"that":[95,117],"bypass":[96],"mechanisms.The":[98],"combines":[100],"two-stage":[101],"LoRA":[102],"fine-tuning,":[103],"DPO-based":[105],"reinforcement":[106],"learning":[107],"optimize":[109],"both":[110],"alignment.Experiments":[115],"show":[116],"significantly":[119],"improves":[120],"achieves":[125],"better":[126],"cross-category":[127],"robustness":[128],"compared":[129],"state-of-the-art":[132],"(SOTA)":[133],"baselines,":[134],"providing":[135],"an":[136],"efficient":[137],"scalable":[139],"tool":[140],"for":[141],"evaluating":[142],"LLM":[143],"safety.":[144]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}