{"id":"https://openalex.org/W7127088984","doi":"https://doi.org/10.1016/j.ipm.2026.104662","title":"Defending LLMs against jailbreak attacks through representation offset detection","display_name":"Defending LLMs against jailbreak attacks through representation offset detection","publication_year":2026,"publication_date":"2026-02-02","ids":{"openalex":"https://openalex.org/W7127088984","doi":"https://doi.org/10.1016/j.ipm.2026.104662"},"language":"en","primary_location":{"id":"doi:10.1016/j.ipm.2026.104662","doi":"https://doi.org/10.1016/j.ipm.2026.104662","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.ipm.2026.104662","pdf_url":null,"source":{"id":"https://openalex.org/S174847851","display_name":"Information Processing & Management","issn_l":"0020-0271","issn":["0020-0271","0306-4573","1873-5371","1878-4089"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-b","fnege-3","jufo-3","norway-2","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Processing &amp; Management","raw_type":"journal-article"},"volume":null,"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/A5124862933","display_name":"Shuo Liu","orcid":"https://orcid.org/0009-0003-1269-3369","observed_orcids":["https://orcid.org/0009-0003-1269-3369"]},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I4392021250","display_name":"State Key Laboratory of Networking and Switching Technology","ror":"https://ror.org/00qtv5q45","country_code":"CN","type":"facility","lineage":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Liu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, No. 10, Xitucheng Road, Haidian District, 100876, Beijing, China","State Key Laboratory of Networking and Switching Technology, No. 10, Xitucheng Road, Haidian District, 100876, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-1269-3369","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, No. 10, Xitucheng Road, Haidian District, 100876, Beijing, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology, No. 10, Xitucheng Road, Haidian District, 100876, Beijing, China","institution_ids":["https://openalex.org/I4392021250"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062327704","display_name":"Xiang Cheng","orcid":"https://orcid.org/0000-0001-6556-2264","observed_orcids":["https://orcid.org/0000-0001-6556-2264"]},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I4392021250","display_name":"State Key Laboratory of Networking and Switching Technology","ror":"https://ror.org/00qtv5q45","country_code":"CN","type":"facility","lineage":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiang Cheng","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, No. 10, Xitucheng Road, Haidian District, 100876, Beijing, China","State Key Laboratory of Networking and Switching Technology, No. 10, Xitucheng Road, Haidian District, 100876, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6556-2264","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, No. 10, Xitucheng Road, Haidian District, 100876, Beijing, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology, No. 10, Xitucheng Road, Haidian District, 100876, Beijing, China","institution_ids":["https://openalex.org/I4392021250"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124760230","display_name":"Zhenzhong Zheng","orcid":"https://orcid.org/0009-0000-7392-9003","observed_orcids":["https://orcid.org/0009-0000-7392-9003"]},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I4392021250","display_name":"State Key Laboratory of Networking and Switching Technology","ror":"https://ror.org/00qtv5q45","country_code":"CN","type":"facility","lineage":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenzhong Zheng","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, No. 10, Xitucheng Road, Haidian District, 100876, Beijing, China","State Key Laboratory of Networking and Switching Technology, No. 10, Xitucheng Road, Haidian District, 100876, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-7392-9003","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, No. 10, Xitucheng Road, Haidian District, 100876, Beijing, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology, No. 10, Xitucheng Road, Haidian District, 100876, Beijing, China","institution_ids":["https://openalex.org/I4392021250"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5140901448","display_name":"Sen Su","orcid":"https://orcid.org/0000-0003-4266-7527","observed_orcids":["https://orcid.org/0000-0003-4266-7527"]},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I4392021250","display_name":"State Key Laboratory of Networking and Switching Technology","ror":"https://ror.org/00qtv5q45","country_code":"CN","type":"facility","lineage":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sen Su","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, No. 10, Xitucheng Road, Haidian District, 100876, Beijing, China","State Key Laboratory of Networking and Switching Technology, No. 10, Xitucheng Road, Haidian District, 100876, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4266-7527","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, No. 10, Xitucheng Road, Haidian District, 100876, Beijing, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology, No. 10, Xitucheng Road, Haidian District, 100876, Beijing, China","institution_ids":["https://openalex.org/I4392021250"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5062327704"],"corresponding_institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4392021250"],"apc_list":{"value":3670,"currency":"USD","value_usd":3670},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06774402,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"63","issue":"5","first_page":"104662","last_page":"104662"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9994999766349792,"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":0.9994999766349792,"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/T11424","display_name":"Security and Verification in Computing","score":9.999999747378752e-05,"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/T10028","display_name":"Topic Modeling","score":0.0,"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/jailbreak-attacks","display_name":"jailbreak attacks","score":0.949999988079071},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8709999918937683},{"id":"https://openalex.org/keywords/attack-detection","display_name":"attack detection","score":0.5770000219345093},{"id":"https://openalex.org/keywords/semantic-bias","display_name":"semantic bias","score":0.7639999985694885},{"id":"https://openalex.org/keywords/intent-extraction","display_name":"intent extraction","score":0.7310000061988831},{"id":"https://openalex.org/keywords/llm-security","display_name":"LLM security","score":0.5989999771118164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6061000227928162},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.5979999899864197},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5252000093460083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44020000100135803},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.4359000027179718},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2522999942302704},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.23330000042915344},{"id":"https://openalex.org/C12174686","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk assessment","level":2,"score":0.21130000054836273},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.20550000667572021}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.ipm.2026.104662","doi":"https://doi.org/10.1016/j.ipm.2026.104662","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.ipm.2026.104662","pdf_url":null,"source":{"id":"https://openalex.org/S174847851","display_name":"Information Processing & Management","issn_l":"0020-0271","issn":["0020-0271","0306-4573","1873-5371","1878-4089"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-b","fnege-3","jufo-3","norway-2","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Processing &amp; Management","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"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":9,"referenced_works":["https://openalex.org/W3126217745","https://openalex.org/W3156636935","https://openalex.org/W4281650088","https://openalex.org/W4309674289","https://openalex.org/W4389617257","https://openalex.org/W4400121375","https://openalex.org/W4402671828","https://openalex.org/W4412888909","https://openalex.org/W4416034915"],"related_works":["https://openalex.org/W4407425033","https://openalex.org/W6979248705","https://openalex.org/W7166824033","https://openalex.org/W6892021687","https://openalex.org/W7128774861","https://openalex.org/W6979227680","https://openalex.org/W7166813312","https://openalex.org/W4412888198","https://openalex.org/W4399252947","https://openalex.org/W7151382798"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-10-27T15:51:10.671819","created_date":"2026-02-03T00:00:00"}
