{"id":"https://openalex.org/W4416035752","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1248","title":"AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender","display_name":"AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035752","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1248"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1248","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1248","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1248","pdf_url":"https://aclanthology.org/2025.emnlp-main.1248.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2025.emnlp-main.1248.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112119688","display_name":"Weixiang Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weixiang Zhao","raw_affiliation_strings":["Harbin Institute of Technology ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology ,","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079151268","display_name":"Jiahe Guo","orcid":"https://orcid.org/0009-0008-8828-8155","observed_orcids":["https://orcid.org/0009-0008-8828-8155"]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahe Guo","raw_affiliation_strings":["Harbin Institute of Technology ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology ,","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068547451","display_name":"Yulin Hu","orcid":"https://orcid.org/0000-0002-1047-9436","observed_orcids":["https://orcid.org/0000-0002-1047-9436"]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yulin Hu","raw_affiliation_strings":["Harbin Institute of Technology ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology ,","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050035602","display_name":"Yang Deng","orcid":"https://orcid.org/0000-0002-8122-5943","observed_orcids":["https://orcid.org/0000-0002-8122-5943"]},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yang Deng","raw_affiliation_strings":["Singapore Management University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Management University","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104325323","display_name":"An Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"An Zhang","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xingyu Sui","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingyu Sui","raw_affiliation_strings":["Harbin Institute of Technology ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology ,","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100948555","display_name":"Xinyang Han","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyang Han","raw_affiliation_strings":["Harbin Institute of Technology ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology ,","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yanyan Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanyan Zhao","raw_affiliation_strings":["Harbin Institute of Technology ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology ,","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113150684","display_name":"Bing Qin","orcid":"https://orcid.org/0000-0002-2543-5604","observed_orcids":["https://orcid.org/0000-0002-2543-5604"]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Qin","raw_affiliation_strings":["Harbin Institute of Technology ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology ,","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089404640","display_name":"Tat\u2010Seng Chua","orcid":"https://orcid.org/0000-0001-6097-7807","observed_orcids":["https://orcid.org/0000-0001-6097-7807"]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tat-Seng Chua","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":null,"display_name":"Ting Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Liu","raw_affiliation_strings":["Harbin Institute of Technology ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology ,","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9066,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.87510633,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"24570","last_page":"24588"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9951000213623047,"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":0.9951000213623047,"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":0.002099999925121665,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.000699999975040555,"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/large-language-models","display_name":"large language models","score":0.675000011920929},{"id":"https://openalex.org/keywords/jailbreak-defense","display_name":"jailbreak defense","score":0.6259999871253967},{"id":"https://openalex.org/keywords/alignment","display_name":"alignment","score":0.5550000071525574},{"id":"https://openalex.org/keywords/adaptive-defense","display_name":"adaptive defense","score":0.5049999952316284},{"id":"https://openalex.org/keywords/adversarial-robustness","display_name":"adversarial robustness","score":0.5770000219345093},{"id":"https://openalex.org/keywords/prompt-engineering","display_name":"prompt engineering","score":0.3779999911785126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5698999762535095},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.40299999713897705},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.29409998655319214},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2915000021457672},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2583000063896179},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.2572999894618988}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.1248","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1248","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1248","pdf_url":"https://aclanthology.org/2025.emnlp-main.1248.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1248","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1248","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1248","pdf_url":"https://aclanthology.org/2025.emnlp-main.1248.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2656429412","display_name":null,"funder_award_id":"62176078","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/F4320322724","display_name":"Ministry of Education, India","ror":"https://ror.org/048xjjh50"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035752.pdf","grobid_xml":"https://content.openalex.org/works/W4416035752.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4412945067","https://openalex.org/W4411119483","https://openalex.org/W7134180830","https://openalex.org/W4404783643","https://openalex.org/W7168187268","https://openalex.org/W4401043746","https://openalex.org/W7140086443","https://openalex.org/W4399554837","https://openalex.org/W4393946427","https://openalex.org/W4411120028"],"abstract_inverted_index":{"Weixiang":[0],"Zhao,":[1,15],"Jiahe":[2],"Guo,":[3],"Yulin":[4],"Hu,":[5],"Yang":[6],"Deng,":[7],"An":[8],"Zhang,":[9],"Xingyu":[10],"Sui,":[11],"Xinyang":[12],"Han,":[13],"Yanyan":[14],"Bing":[16],"Qin,":[17],"Tat-Seng":[18],"Chua,":[19],"Ting":[20],"Liu.":[21],"Proceedings":[22],"of":[23],"the":[24],"2025":[25],"Conference":[26],"on":[27],"Empirical":[28],"Methods":[29],"in":[30],"Natural":[31],"Language":[32],"Processing.":[33],"2025.":[34]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2025-11-08T00:00:00"}
