{"id":"https://openalex.org/W4408612358","doi":"https://doi.org/10.1145/3724393","title":"<scp>JailGuard</scp> : A Universal Detection Framework for Prompt-based Attacks on LLM Systems","display_name":"<scp>JailGuard</scp> : A Universal Detection Framework for Prompt-based Attacks on LLM Systems","publication_year":2025,"publication_date":"2025-03-19","ids":{"openalex":"https://openalex.org/W4408612358","doi":"https://doi.org/10.1145/3724393"},"language":"en","primary_location":{"id":"doi:10.1145/3724393","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3724393","pdf_url":null,"source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092424261","display_name":"Xiaoyu Zhang","orcid":"https://orcid.org/0000-0001-7010-6749"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyu Zhang","raw_affiliation_strings":["Xi\u2019an Jiaotong University, Xi\u2019an, China","Xi\u2019an Jiaotong University, China"],"raw_orcid":"https://orcid.org/0000-0001-7010-6749","affiliations":[{"raw_affiliation_string":"Xi\u2019an Jiaotong University, Xi\u2019an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"Xi\u2019an Jiaotong University, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071275263","display_name":"Cen Zhang","orcid":"https://orcid.org/0000-0001-5603-1322"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Cen Zhang","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore","Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-5603-1322","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101674538","display_name":"Tianlin Li","orcid":"https://orcid.org/0000-0002-2207-1622"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tianlin Li","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore","Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-2207-1622","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036183844","display_name":"Yihao Huang","orcid":"https://orcid.org/0000-0002-5784-770X"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yihao Huang","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore","Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-5784-770X","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084784341","display_name":"Xiaojun Jia","orcid":"https://orcid.org/0000-0002-2018-9344"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xiaojun Jia","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore","Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-2018-9344","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017425520","display_name":"Ming Hu","orcid":"https://orcid.org/0000-0002-5058-4660"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ming Hu","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore","Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-5058-4660","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100436740","display_name":"Jie Zhang","orcid":"https://orcid.org/0000-0002-4230-1077"},"institutions":[{"id":"https://openalex.org/I4210161496","display_name":"A*STAR Graduate Academy","ror":"https://ror.org/059yjzn93","country_code":"SG","type":"education","lineage":["https://openalex.org/I115228651","https://openalex.org/I4210161496"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jie Zhang","raw_affiliation_strings":["CFAR, A*STAR, Singapore, Singapore","CFAR, A*STAR, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4230-1077","affiliations":[{"raw_affiliation_string":"CFAR, A*STAR, Singapore, Singapore","institution_ids":["https://openalex.org/I4210161496"]},{"raw_affiliation_string":"CFAR, A*STAR, Singapore","institution_ids":["https://openalex.org/I4210161496"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100355692","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0001-7300-9215"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore","Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-7300-9215","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101594068","display_name":"Shiqing Ma","orcid":"https://orcid.org/0000-0003-1551-8948"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiqing Ma","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, Massachusetts, USA","University of Massachusetts, Amherst, United States"],"raw_orcid":"https://orcid.org/0000-0003-1551-8948","affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, Massachusetts, USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University of Massachusetts, Amherst, United States","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101843177","display_name":"Chao Shen","orcid":"https://orcid.org/0000-0002-6959-0569"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Shen","raw_affiliation_strings":["Xi\u2019an Jiaotong University, Xi\u2019an, China","Xi\u2019an Jiaotong University, China"],"raw_orcid":"https://orcid.org/0000-0002-6959-0569","affiliations":[{"raw_affiliation_string":"Xi\u2019an Jiaotong University, Xi\u2019an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"Xi\u2019an Jiaotong University, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.6921,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.98482864,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"35","issue":"1","first_page":"1","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10400","display_name":"Network Security and Intrusion Detection","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9980000257492065,"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/computer-science","display_name":"Computer science","score":0.7921088933944702},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.4134845733642578}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7921088933944702},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.4134845733642578}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3724393","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3724393","pdf_url":null,"source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4458655729","display_name":null,"funder_award_id":"62006181, 62132011, 62161160337, 62206217, U20A20177, U21B2018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1980867644","https://openalex.org/W2081580037","https://openalex.org/W2112364454","https://openalex.org/W2135198734","https://openalex.org/W2465309725","https://openalex.org/W2888233014","https://openalex.org/W3031251962","https://openalex.org/W3035524453","https://openalex.org/W3035682985","https://openalex.org/W3087885918","https://openalex.org/W3100992758","https://openalex.org/W3163504421","https://openalex.org/W3180181113","https://openalex.org/W3196750896","https://openalex.org/W3204913553","https://openalex.org/W3212752805","https://openalex.org/W4206655182","https://openalex.org/W4214540501","https://openalex.org/W4220891756","https://openalex.org/W4230172274","https://openalex.org/W4233907442","https://openalex.org/W4239025696","https://openalex.org/W4287019050","https://openalex.org/W4313476697","https://openalex.org/W4384520874","https://openalex.org/W4386071537","https://openalex.org/W4387245383","https://openalex.org/W4387587690","https://openalex.org/W4388886073","https://openalex.org/W4389617257","https://openalex.org/W4399932475","https://openalex.org/W4400484590","https://openalex.org/W4400484607"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"The":[0,168],"systems":[1,27,98],"and":[2,10,104,129,154,157,190,198],"software":[3],"powered":[4],"by":[5,196],"Large":[6,12],"Language":[7,13],"Models":[8,14],"(LLMs)":[9],"Multi-Modal":[11],"(MLLMs)":[15],"have":[16],"played":[17],"a":[18,89,159],"critical":[19],"role":[20],"in":[21,72,75],"numerous":[22],"scenarios.":[23],"However,":[24],"current":[25],"LLM":[26,38,49,97],"are":[28,65,114],"vulnerable":[29],"to":[30,40,51,68,126,141,163],"prompt-based":[31,100],"attacks,":[32,70],"with":[33],"jailbreaking":[34],"attacks":[35,46,78,101,113],"enabling":[36],"the":[37,48,56,110,131,134,138,171,182],"system":[39,50],"generate":[41,127],"harmful":[42],"content,":[43],"while":[44],"hijacking":[45],"manipulate":[47],"perform":[52],"attacker-desired":[53],"tasks,":[54],"underscoring":[55],"necessity":[57],"for":[58,99,152],"detection":[59,91,166,184],"tools.":[60],"Unfortunately,":[61],"existing":[62],"detecting":[63,76],"approaches":[64],"usually":[66],"tailored":[67],"specific":[69],"resulting":[71],"poor":[73],"generalization":[74],"various":[77],"across":[79,102],"different":[80],"modalities.":[81,106],"To":[82],"address":[83],"it,":[84],"we":[85],"propose":[86],"JailGuard":[87,107,122,180],",":[88],"universal":[90],"framework":[92],"deployed":[93],"on":[94,109,137,170,188],"top":[95],"of":[96,133,186],"text":[103,153,189],"image":[105,155,191],"operates":[108],"principle":[111],"that":[112,179],"inherently":[115],"less":[116],"robust":[117],"than":[118],"benign":[119,146],"ones.":[120],"Specifically,":[121],"mutates":[123],"untrusted":[124],"inputs":[125,156],"variants":[128],"leverages":[130],"discrepancy":[132],"variants\u2019":[135],"responses":[136],"target":[139],"model":[140],"distinguish":[142],"attack":[143,176],"samples":[144],"from":[145],"samples.":[147],"We":[148],"implement":[149],"18":[150],"mutators":[151],"design":[158],"mutator":[160],"combination":[161],"policy":[162],"further":[164],"improve":[165],"generalization.":[167],"evaluation":[169],"dataset":[172],"containing":[173],"15":[174],"known":[175],"types":[177],"suggests":[178],"achieves":[181],"best":[183],"accuracy":[185],"86.14%/82.90%":[187],"inputs,":[192],"outperforming":[193],"state-of-the-art":[194],"methods":[195],"11.81\u201325.73%":[197],"12.20\u201321.40%.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":9}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}