{"id":"https://openalex.org/W4411552743","doi":"https://doi.org/10.1109/cscwd64889.2025.11033427","title":"A Jailbreak Prompt Detector Based on Selective Perturbation and Contrastive Learning","display_name":"A Jailbreak Prompt Detector Based on Selective Perturbation and Contrastive Learning","publication_year":2025,"publication_date":"2025-05-05","ids":{"openalex":"https://openalex.org/W4411552743","doi":"https://doi.org/10.1109/cscwd64889.2025.11033427"},"language":"en","primary_location":{"id":"doi:10.1109/cscwd64889.2025.11033427","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cscwd64889.2025.11033427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 28th International Conference on Computer Supported Cooperative Work in Design (CSCWD)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101589348","display_name":"Yanshu Li","orcid":"https://orcid.org/0000-0002-2902-7034"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanshu Li","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115589913","display_name":"Yan Wang","orcid":"https://orcid.org/0009-0002-3286-3516"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Wang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104328511","display_name":"Haitian Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haitian Yang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100763678","display_name":"Wen Liu","orcid":"https://orcid.org/0000-0002-3584-628X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Liu","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100773110","display_name":"Li Ning","orcid":"https://orcid.org/0000-0002-3246-7057"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Li","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1838","last_page":"1843"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9908000230789185,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9908000230789185,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9652000069618225,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9632999897003174,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.6756365299224854},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.576185941696167},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39951440691947937},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09669283032417297}],"concepts":[{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.6756365299224854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.576185941696167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39951440691947937},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09669283032417297}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cscwd64889.2025.11033427","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cscwd64889.2025.11033427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 28th International Conference on Computer Supported Cooperative Work in Design (CSCWD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320326972","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2295598076","https://openalex.org/W2973226110","https://openalex.org/W4402667010","https://openalex.org/W4402683786","https://openalex.org/W4404518370","https://openalex.org/W4405181600","https://openalex.org/W6769627184","https://openalex.org/W6776700526","https://openalex.org/W6810738896"],"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/W2366906938"],"abstract_inverted_index":{"Jailbreak":[0],"attacks":[1,126],"pose":[2],"a":[3,53,99],"significant":[4],"threat":[5],"to":[6,44,82,92,112,139,147],"the":[7,66,84,123,135,152,155],"reliable":[8],"deployment":[9],"of":[10,68,151,157],"large":[11],"language":[12],"models":[13],"(LLMs)":[14],"in":[15],"critical":[16],"applications.":[17],"Although":[18],"existing":[19],"LLMs":[20],"are":[21],"supervised":[22,109],"fine-tuning":[23],"and":[24,61,117,127],"aligned":[25],"through":[26,74],"reinforcement":[27],"learning":[28,111],"from":[29,95],"human":[30],"feedback,":[31],"automated":[32],"jailbreak":[33,40,54,69,88,116,125],"attack":[34,55],"algorithms":[35],"can":[36],"still":[37],"identify":[38],"potential":[39],"prompts":[41],"that":[42,131],"lead":[43],"harmful":[45],"outputs.":[46],"In":[47,90],"this":[48],"paper,":[49],"we":[50,97,107],"propose":[51],"JPS,":[52],"detector":[56],"based":[57,102],"on":[58,103,122],"selective":[59,100],"perturbation":[60,80],"contrastive":[62,110],"learning.":[63],"JPS":[64,132],"leverages":[65],"robustness":[67],"attacks,":[70],"which":[71],"is":[72],"achieved":[73],"complex":[75],"multi-step":[76],"optimization,":[77],"by":[78],"using":[79],"methods":[81],"enhance":[83],"training":[85],"data":[86],"for":[87],"prompts.":[89],"order":[91],"mitigate":[93],"noise":[94],"perturbation,":[96],"introduce":[98],"strategy":[101],"token":[104],"importance.":[105],"Additionally,":[106],"employ":[108],"effectively":[113],"differentiate":[114],"between":[115],"benign":[118,128],"samples.":[119],"Extensive":[120],"experiments":[121,144],"popular":[124],"datasets":[129],"show":[130],"outperforms":[133],"all":[134],"baseline":[136],"approaches":[137],"according":[138],"F1-score.":[140],"Furthermore,":[141],"detailed":[142],"ablation":[143],"were":[145],"conducted":[146],"analyze":[148],"each":[149],"module":[150],"model,":[153],"demonstrating":[154],"effectiveness":[156],"our":[158],"approach.":[159]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}