{"id":"https://openalex.org/W4411551265","doi":"https://doi.org/10.1109/cscwd64889.2025.11033375","title":"DS-GCG: Enhancing LLM Jailbreaks with Token Suppression and Induction Dual-Strategy","display_name":"DS-GCG: Enhancing LLM Jailbreaks with Token Suppression and Induction Dual-Strategy","publication_year":2025,"publication_date":"2025-05-05","ids":{"openalex":"https://openalex.org/W4411551265","doi":"https://doi.org/10.1109/cscwd64889.2025.11033375"},"language":"en","primary_location":{"id":"doi:10.1109/cscwd64889.2025.11033375","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cscwd64889.2025.11033375","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":"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/A5047580108","display_name":"Xuehai Tang","orcid":"https://orcid.org/0000-0002-9901-4087"},"institutions":[{"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"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xuehai Tang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049361628","display_name":"Xikang Yang","orcid":"https://orcid.org/0000-0002-3404-906X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","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":"Xikang Yang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103732500","display_name":"Zhongjiang Yao","orcid":"https://orcid.org/0000-0001-6583-9526"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","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":"Zhongjiang Yao","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091166192","display_name":"Jie Wen","orcid":"https://orcid.org/0000-0002-4959-0692"},"institutions":[{"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"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Wen","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077793776","display_name":"Xi Zhou","orcid":"https://orcid.org/0000-0001-6922-9856"},"institutions":[{"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"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Zhou","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112539471","display_name":"Jizhong Han","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","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":"Jizhong Han","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018288181","display_name":"Songlin Hu","orcid":"https://orcid.org/0000-0002-7170-3809"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","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":"Songlin Hu","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5047580108"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"],"apc_list":null,"apc_paid":null,"fwci":6.9916,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.96563233,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"273","last_page":"278"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12034","display_name":"Digital and Cyber Forensics","score":0.9695000052452087,"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"}},"topics":[{"id":"https://openalex.org/T12034","display_name":"Digital and Cyber Forensics","score":0.9695000052452087,"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"}},{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9383000135421753,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9253000020980835,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6319255232810974},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5940720438957214},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.46907350420951843},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3305957317352295},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1730298399925232},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1081705391407013},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.0892685055732727}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6319255232810974},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5940720438957214},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46907350420951843},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3305957317352295},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1730298399925232},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1081705391407013},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.0892685055732727},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cscwd64889.2025.11033375","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cscwd64889.2025.11033375","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":[{"display_name":"Gender equality","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W4226278401","https://openalex.org/W4384918448","https://openalex.org/W4385374425","https://openalex.org/W4386907292","https://openalex.org/W4387436590","https://openalex.org/W4387559087","https://openalex.org/W4387635776","https://openalex.org/W4388132131","https://openalex.org/W4388482289","https://openalex.org/W4388788749","https://openalex.org/W4389364443","https://openalex.org/W4390897498","https://openalex.org/W4391912894","https://openalex.org/W4391940619","https://openalex.org/W4392223570","https://openalex.org/W4396239636","https://openalex.org/W4399553916","https://openalex.org/W6858023062","https://openalex.org/W6862724468"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700"],"abstract_inverted_index":{"In":[0],"intelligent":[1],"collaborative":[2],"systems,":[3],"the":[4,39,66,74,166,170],"role":[5],"of":[6,21,42,69,78,173],"Large":[7],"Language":[8],"Models":[9],"(LLMs)":[10],"is":[11,81],"becoming":[12],"increasingly":[13],"significant,":[14],"with":[15,127],"their":[16,89],"security":[17,40],"and":[18,55,88,122,153],"privacy":[19],"being":[20],"paramount":[22],"importance.":[23],"Greedy":[24],"Coordinate":[25],"Gradient":[26],"(GCG)-based":[27],"adversarial":[28,86,106,136],"approaches":[29],"are":[30,47],"a":[31,82,128],"staple":[32],"in":[33,73],"red":[34],"team":[35],"testing":[36],"for":[37],"circumventing":[38],"alignments":[41],"LLMs.":[43],"Yet,":[44],"these":[45,99],"methods":[46],"challenged":[48],"by":[49],"issues":[50],"such":[51],"as":[52],"convergence":[53],"difficulties":[54],"pseudo-evasion,":[56],"which":[57],"can":[58,91],"impede":[59],"attack":[60,94,107,112],"efficacy.":[61],"Our":[62,157],"research":[63],"indicates":[64],"that":[65,109],"high":[67],"likelihood":[68],"rejection":[70],"tokens":[71],"appearing":[72],"initial":[75],"k":[76],"positions":[77],"generated":[79],"text":[80],"major":[83],"contributor":[84],"to":[85,118,133],"failures,":[87],"suppression":[90],"significantly":[92],"improve":[93],"success":[95],"rates.":[96],"Building":[97],"on":[98,160,165],"insights,":[100],"we":[101],"present":[102],"DS-GCG,":[103],"an":[104,151],"innovative":[105],"methodology":[108],"enhances":[110],"GCG":[111],"potency.":[113],"It":[114],"employs":[115],"adjustable-position":[116],"prefilling":[117],"quell":[119],"refusal":[120],"responses":[121],"incite":[123],"harmful":[124],"outputs,":[125],"coupled":[126],"bidirectional":[129],"greedy":[130],"gradient":[131],"search":[132,155],"swiftly":[134],"identify":[135],"suffixes.":[137],"DS-GCG's":[138],"universal":[139],"suffix":[140],"approach":[141],"not":[142],"only":[143],"mitigates":[144],"refusals":[145],"but":[146],"also":[147],"hastens":[148],"convergence,":[149],"offering":[150],"efficient":[152],"robust":[154],"strategy.":[156],"experimental":[158],"results":[159],"widely-used":[161],"open-source":[162],"LLMs,":[163],"showcased":[164],"AdvBench":[167],"dataset,":[168],"confirm":[169],"cutting-edge":[171],"performance":[172],"DS-GCG.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}