{"id":"https://openalex.org/W4405219474","doi":"https://doi.org/10.1093/comjnl/bxae124","title":"Can LLMs deeply detect complex malicious queries? A framework for jailbreaking via obfuscating intent","display_name":"Can LLMs deeply detect complex malicious queries? A framework for jailbreaking via obfuscating intent","publication_year":2024,"publication_date":"2024-12-09","ids":{"openalex":"https://openalex.org/W4405219474","doi":"https://doi.org/10.1093/comjnl/bxae124"},"language":"en","primary_location":{"id":"doi:10.1093/comjnl/bxae124","is_oa":false,"landing_page_url":"https://doi.org/10.1093/comjnl/bxae124","pdf_url":null,"source":{"id":"https://openalex.org/S44643521","display_name":"The Computer Journal","issn_l":"0010-4620","issn":["0010-4620","1460-2067"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Computer Journal","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/A5065104731","display_name":"Shang Shang","orcid":"https://orcid.org/0009-0001-7596-3018"},"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"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shang Shang","raw_affiliation_strings":["Institute of Information Engineering , Chinese Academy of Sciences, No. 19 Shucun Rd. Haidian District, 100085 Beijing,","School of Cyber Security , University of Chinese Academy of Sciences, NO. 19 Yuquan Rd. Shijingshan District, 100049 Beijing,","School of Cyber Security, University of Chinese Academy of Sciences, NO. 19 Yuquan Rd. Shijingshan District, 100049 Beijing, China","Institute of Information Engineering, Chinese Academy of Sciences, No. 19 Shucun Rd. Haidian District, 100085 Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering , Chinese Academy of Sciences, No. 19 Shucun Rd. Haidian District, 100085 Beijing,","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Cyber Security , University of Chinese Academy of Sciences, NO. 19 Yuquan Rd. Shijingshan District, 100049 Beijing,","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"School of Cyber Security, University of Chinese Academy of Sciences, NO. 19 Yuquan Rd. Shijingshan District, 100049 Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, No. 19 Shucun Rd. Haidian District, 100085 Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083387424","display_name":"Xinqiang Zhao","orcid":"https://orcid.org/0000-0002-9399-7289"},"institutions":[{"id":"https://openalex.org/I4210162213","display_name":"China Electronics Standardization Institute","ror":"https://ror.org/05hxrpj87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210162213","https://openalex.org/I890469752"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinqiang Zhao","raw_affiliation_strings":["China Electronics Standardization Institute , No. 1, Andingmen East Street, Dongcheng District, 100007 Beijing,","School of Cyber Security , University of Chinese Academy of Sciences, NO. 19 Yuquan Rd. Shijingshan District, 100049 Beijing,","School of Cyber Security, University of Chinese Academy of Sciences, NO. 19 Yuquan Rd. Shijingshan District, 100049 Beijing, China","China Electronics Standardization Institute, No. 1, Andingmen East Street, Dongcheng District, 100007 Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Electronics Standardization Institute , No. 1, Andingmen East Street, Dongcheng District, 100007 Beijing,","institution_ids":["https://openalex.org/I4210162213"]},{"raw_affiliation_string":"School of Cyber Security , University of Chinese Academy of Sciences, NO. 19 Yuquan Rd. Shijingshan District, 100049 Beijing,","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"School of Cyber Security, University of Chinese Academy of Sciences, NO. 19 Yuquan Rd. Shijingshan District, 100049 Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"China Electronics Standardization Institute, No. 1, Andingmen East Street, Dongcheng District, 100007 Beijing, China","institution_ids":["https://openalex.org/I4210162213"]}]},{"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":"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":"Zhongjiang Yao","raw_affiliation_strings":["Institute of Information Engineering , Chinese Academy of Sciences, No. 19 Shucun Rd. Haidian District, 100085 Beijing,","Institute of Information Engineering, Chinese Academy of Sciences, No. 19 Shucun Rd. Haidian District, 100085 Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering , Chinese Academy of Sciences, No. 19 Shucun Rd. Haidian District, 100085 Beijing,","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, No. 19 Shucun Rd. Haidian District, 100085 Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044754708","display_name":"Yepeng Yao","orcid":"https://orcid.org/0000-0002-2669-4915"},"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":"Yepeng Yao","raw_affiliation_strings":["Institute of Information Engineering , Chinese Academy of Sciences, No. 19 Shucun Rd. Haidian District, 100085 Beijing,","Institute of Information Engineering, Chinese Academy of Sciences, No. 19 Shucun Rd. Haidian District, 100085 Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering , Chinese Academy of Sciences, No. 19 Shucun Rd. Haidian District, 100085 Beijing,","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, No. 19 Shucun Rd. Haidian District, 100085 Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031351418","display_name":"Liya Su","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liya Su","raw_affiliation_strings":["Security Lab , JD Cloud, Beijing,","Security Lab, JD Cloud, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Security Lab , JD Cloud, Beijing,","institution_ids":[]},{"raw_affiliation_string":"Security Lab, JD Cloud, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044920156","display_name":"Zijing Fan","orcid":"https://orcid.org/0009-0008-3192-9919"},"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":"Zijing Fan","raw_affiliation_strings":["Institute of Information Engineering , Chinese Academy of Sciences, No. 19 Shucun Rd. Haidian District, 100085 Beijing,","Institute of Information Engineering, Chinese Academy of Sciences, No. 19 Shucun Rd. Haidian District, 100085 Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering , Chinese Academy of Sciences, No. 19 Shucun Rd. Haidian District, 100085 Beijing,","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, No. 19 Shucun Rd. Haidian District, 100085 Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100356760","display_name":"Xiaodan Zhang","orcid":"https://orcid.org/0000-0003-3579-953X"},"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":"Xiaodan Zhang","raw_affiliation_strings":["Institute of Information Engineering , Chinese Academy of Sciences, No. 19 Shucun Rd. Haidian District, 100085 Beijing,","Institute of Information Engineering, Chinese Academy of Sciences, No. 19 Shucun Rd. Haidian District, 100085 Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering , Chinese Academy of Sciences, No. 19 Shucun Rd. Haidian District, 100085 Beijing,","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, No. 19 Shucun Rd. Haidian District, 100085 Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007843747","display_name":"Zhengwei Jiang","orcid":"https://orcid.org/0000-0003-2425-7081"},"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"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengwei Jiang","raw_affiliation_strings":["Institute of Information Engineering , Chinese Academy of Sciences, No. 19 Shucun Rd. Haidian District, 100085 Beijing,","School of Cyber Security , University of Chinese Academy of Sciences, NO. 19 Yuquan Rd. Shijingshan District, 100049 Beijing,","Institute of Information Engineering, Chinese Academy of Sciences, No. 19 Shucun Rd. Haidian District, 100085 Beijing, China","School of Cyber Security, University of Chinese Academy of Sciences, NO. 19 Yuquan Rd. Shijingshan District, 100049 Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering , Chinese Academy of Sciences, No. 19 Shucun Rd. Haidian District, 100085 Beijing,","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Cyber Security , University of Chinese Academy of Sciences, NO. 19 Yuquan Rd. Shijingshan District, 100049 Beijing,","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, No. 19 Shucun Rd. Haidian District, 100085 Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Cyber Security, University of Chinese Academy of Sciences, NO. 19 Yuquan Rd. Shijingshan District, 100049 Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5065104731"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404","https://openalex.org/I4210165038"],"apc_list":{"value":2635,"currency":"GBP","value_usd":3232},"apc_paid":null,"fwci":2.2028,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.89861516,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"68","issue":"5","first_page":"460","last_page":"478"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9994000196456909,"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":0.9994000196456909,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9850000143051147,"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/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.9832000136375427,"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/ambiguity","display_name":"Ambiguity","score":0.8347128629684448},{"id":"https://openalex.org/keywords/vulnerability","display_name":"Vulnerability (computing)","score":0.7069994807243347},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.693569004535675},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.5479632616043091},{"id":"https://openalex.org/keywords/internet-privacy","display_name":"Internet privacy","score":0.5263453722000122},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4735528528690338}],"concepts":[{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.8347128629684448},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.7069994807243347},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.693569004535675},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.5479632616043091},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.5263453722000122},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4735528528690338},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1093/comjnl/bxae124","is_oa":false,"landing_page_url":"https://doi.org/10.1093/comjnl/bxae124","pdf_url":null,"source":{"id":"https://openalex.org/S44643521","display_name":"The Computer Journal","issn_l":"0010-4620","issn":["0010-4620","1460-2067"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Computer Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality","score":0.44999998807907104}],"awards":[{"id":"https://openalex.org/G1301344488","display_name":null,"funder_award_id":"2022159","funder_id":"https://openalex.org/F4320322847","funder_display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences"},{"id":"https://openalex.org/G8372602484","display_name":null,"funder_award_id":"62202466","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"},{"id":"https://openalex.org/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W2914304175","https://openalex.org/W2949128310","https://openalex.org/W2962718684","https://openalex.org/W4212774754","https://openalex.org/W4223908421","https://openalex.org/W4292779060","https://openalex.org/W4298181573","https://openalex.org/W4305001257","https://openalex.org/W4376312605","https://openalex.org/W4378506863","https://openalex.org/W4384918632","https://openalex.org/W4385374425","https://openalex.org/W4385452929","https://openalex.org/W4385571804","https://openalex.org/W4385894687","https://openalex.org/W4386043398","https://openalex.org/W4386044169","https://openalex.org/W4386721882","https://openalex.org/W4386907292","https://openalex.org/W4386942538","https://openalex.org/W4387430709","https://openalex.org/W4387436631","https://openalex.org/W4387559087","https://openalex.org/W4387561119","https://openalex.org/W4387724711","https://openalex.org/W4388327713","https://openalex.org/W4388488609","https://openalex.org/W4388886073","https://openalex.org/W4389279097","https://openalex.org/W4389518968","https://openalex.org/W4389519367","https://openalex.org/W4389519948","https://openalex.org/W4392904091","https://openalex.org/W4401615053","https://openalex.org/W4404782326","https://openalex.org/W4404783461","https://openalex.org/W4405181600","https://openalex.org/W6737564900","https://openalex.org/W6778883912","https://openalex.org/W6803084059","https://openalex.org/W6809583738","https://openalex.org/W6810738896","https://openalex.org/W6843975101","https://openalex.org/W6845894799","https://openalex.org/W6849994323","https://openalex.org/W6851985269","https://openalex.org/W6852755587","https://openalex.org/W6853601813","https://openalex.org/W6853821718","https://openalex.org/W6855469472","https://openalex.org/W6855759525","https://openalex.org/W6855927874","https://openalex.org/W6856398428","https://openalex.org/W6856424530","https://openalex.org/W6856601796","https://openalex.org/W6856768101","https://openalex.org/W6856800273","https://openalex.org/W6857038892","https://openalex.org/W6857049399","https://openalex.org/W6857257659","https://openalex.org/W6857290827","https://openalex.org/W6857485033","https://openalex.org/W6857608907"],"related_works":["https://openalex.org/W2906845177","https://openalex.org/W4200107511","https://openalex.org/W2891427086","https://openalex.org/W3048799479","https://openalex.org/W1968625315","https://openalex.org/W3006507989","https://openalex.org/W2779961139","https://openalex.org/W4240241597","https://openalex.org/W2763500028","https://openalex.org/W4240288358"],"abstract_inverted_index":{"Abstract":[0],"This":[1,134],"paper":[2],"delves":[3],"into":[4],"a":[5,53,118,126,244],"possible":[6],"security":[7,278],"flaw":[8],"in":[9,15,48,56,93],"large":[10],"language":[11],"models":[12],"(LLMs),":[13],"particularly":[14],"their":[16,57,102,158],"capacity":[17],"to":[18,44,77,89,100,151,186],"identify":[19],"malicious":[20,35,91,192],"intent":[21,92],"within":[22,169],"intricate":[23],"or":[24],"ambiguous":[25],"inquiries.":[26],"We":[27,163,194],"have":[28,96],"discovered":[29],"that":[30,95],"LLMs":[31,150],"might":[32],"overlook":[33],"the":[34,45,106,137,142,180,189,197,200,264],"nature":[36],"of":[37,70,184,191,199,218,236,246,267],"highly":[38],"veiled":[39],"requests,":[40],"even":[41],"without":[42],"alterations":[43],"malevolent":[46,107],"text":[47],"those":[49],"queries,":[50,84],"thus":[51],"exposing":[52],"significant":[54],"weakness":[55],"content":[58,108,155,160,248,277],"analysis":[59],"systems.":[60],"To":[61,110],"be":[62],"specific,":[63],"we":[64,116,239],"pinpoint":[65],"and":[66,85,112,121,124,156,174,182,210,259],"scrutinize":[67],"two":[68,166],"aspects":[69],"this":[71,114,170],"vulnerability:":[72],"(i)":[73],"LLMs\u2019":[74,87],"diminished":[75],"capability":[76],"perceive":[78],"maliciousness":[79],"when":[80],"parsing":[81],"extremely":[82],"obscured":[83],"(ii)":[86],"inability":[88],"discern":[90],"queries":[94,185],"been":[97],"intentionally":[98],"altered":[99],"increase":[101],"ambiguity":[103,183],"by":[104,140],"modifying":[105],"itself.":[109],"illustrate":[111],"tackle":[113],"problem,":[115],"propose":[117],"theoretical":[119],"framework":[120],"analytical":[122],"strategy,":[123],"introduce":[125],"novel":[127],"black-box":[128],"jailbreak":[129,215],"attack":[130],"technique":[131,135],"called":[132],"IntentObfuscator.":[133],"exploits":[136],"identified":[138],"vulnerability":[139],"concealing":[141],"genuine":[143],"intentions":[144],"behind":[145],"user":[146],"prompts,":[147],"thereby":[148],"compelling":[149],"inadvertently":[152],"produce":[153],"restricted":[154],"circumvent":[157],"inherent":[159],"safety":[161],"protocols.":[162],"elaborate":[164],"on":[165,223,270],"specific":[167],"applications":[168],"framework:":[171],"\u201dObscure":[172],"Intention\u201d":[173],"\u201dCreate":[175],"Ambiguity,\u201d":[176],"which":[177],"skillfully":[178],"manipulate":[179],"complexity":[181],"effectively":[187],"dodge":[188],"detection":[190],"intent.":[193],"empirically":[195],"confirm":[196],"efficacy":[198],"IntentObfuscator":[201],"approach":[202,242],"across":[203,243],"various":[204],"models,":[205],"including":[206,250],"ChatGPT-3.5,":[207,224],"ChatGPT-4,":[208],"Qwen,":[209],"Baichuan,":[211],"achieving":[212],"an":[213,232],"average":[214],"success":[216,234],"rate":[217,235],"69.21%.":[219],"Remarkably,":[220],"our":[221,241,268],"tests":[222],"boasting":[225],"100":[226],"million":[227],"weekly":[228],"active":[229],"users,":[230],"yielded":[231],"impressive":[233],"83.65%.":[237],"Additionally,":[238],"verify":[240],"range":[245],"sensitive":[247],"categories,":[249],"graphic":[251],"violence,":[252],"racism,":[253],"sexism,":[254],"political":[255],"sensitivity,":[256],"cybersecurity":[257],"threats,":[258],"criminal":[260],"techniques,":[261],"further":[262],"highlighting":[263],"considerable":[265],"impact":[266],"findings":[269],"refining":[271],"\u201dRed":[272],"Team\u201d":[273],"tactics":[274],"against":[275],"LLM":[276],"frameworks.":[279]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
