{"id":"https://openalex.org/W7166813312","doi":"https://doi.org/10.18653/v1/2026.acl-long.125","title":"Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning","display_name":"Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166813312","doi":"https://doi.org/10.18653/v1/2026.acl-long.125"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.125","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.125","pdf_url":"https://aclanthology.org/2026.acl-long.125.pdf","source":null,"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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.125.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122125527","display_name":"Rui Pu","orcid":null},"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/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Pu","raw_affiliation_strings":["Key Laboratory of Trustworthy Distributed Computing and Service (MoE) , Beijing University of Posts and Telecommunications , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Trustworthy Distributed Computing and Service (MoE) , Beijing University of Posts and Telecommunications , China","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4210139618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139723260","display_name":"Chaozhuo Li","orcid":null},"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/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaozhuo Li","raw_affiliation_strings":["Key Laboratory of Trustworthy Distributed Computing and Service (MoE) , Beijing University of Posts and Telecommunications , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Trustworthy Distributed Computing and Service (MoE) , Beijing University of Posts and Telecommunications , China","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4210139618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114601765","display_name":"Rui Ha","orcid":null},"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/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Ha","raw_affiliation_strings":["Key Laboratory of Trustworthy Distributed Computing and Service (MoE) , Beijing University of Posts and Telecommunications , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Trustworthy Distributed Computing and Service (MoE) , Beijing University of Posts and Telecommunications , China","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4210139618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139745694","display_name":"Litian Zhang","orcid":null},"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/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Litian Zhang","raw_affiliation_strings":["Key Laboratory of Trustworthy Distributed Computing and Service (MoE) , Beijing University of Posts and Telecommunications , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Trustworthy Distributed Computing and Service (MoE) , Beijing University of Posts and Telecommunications , China","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4210139618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139720144","display_name":"Lirong Qiu","orcid":null},"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/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lirong Qiu","raw_affiliation_strings":["Key Laboratory of Trustworthy Distributed Computing and Service (MoE) , Beijing University of Posts and Telecommunications , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Trustworthy Distributed Computing and Service (MoE) , Beijing University of Posts and Telecommunications , China","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4210139618"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139796463","display_name":"Xi Zhang","orcid":null},"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/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Zhang","raw_affiliation_strings":["Key Laboratory of Trustworthy Distributed Computing and Service (MoE) , Beijing University of Posts and Telecommunications , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Trustworthy Distributed Computing and Service (MoE) , Beijing University of Posts and Telecommunications , China","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4210139618"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":20.5842,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.99229568,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2742","last_page":"2759"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.7627000212669373,"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":0.7627000212669373,"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":0.05689999833703041,"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":0.017799999564886093,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.2540999948978424},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.2540999948978424},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2483000010251999},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.23960000276565552},{"id":"https://openalex.org/keywords/government","display_name":"Government (linguistics)","score":0.23810000717639923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5181000232696533},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.4433000087738037},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2483000010251999},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24729999899864197},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.23960000276565552},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"score":0.23810000717639923},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.23389999568462372},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.23229999840259552}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.125","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.125","pdf_url":"https://aclanthology.org/2026.acl-long.125.pdf","source":null,"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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.125","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.125","pdf_url":"https://aclanthology.org/2026.acl-long.125.pdf","source":null,"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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321470","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166813312.pdf","grobid_xml":"https://content.openalex.org/works/W7166813312.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Defending":[0],"large":[1],"language":[2],"models":[3],"(LLMs)":[4],"against":[5],"jailbreak":[6,49,144],"attacks":[7],"is":[8,118],"essential":[9],"for":[10],"their":[11],"safe":[12],"and":[13,29,79,101,126,138],"reliable":[14],"deployment.Existing":[15],"defenses":[16],"often":[17],"rely":[18],"on":[19,92],"shallow":[20],"pattern":[21],"matching,":[22],"which":[23,43],"struggles":[24],"to":[25,27,85,99,109,120,142],"generalize":[26],"novel":[28],"unseen":[30,110,143],"attack":[31],"strategies.To":[32],"address":[33],"this":[34,93],"challenge,":[35],"we":[36],"propose":[37],"the":[38,45,77,96],"Cognitive-Driven":[39],"Defense":[40],"(CDD)":[41],"framework,":[42],"targets":[44],"underlying":[46],"structure":[47],"of":[48,76,123,128],"prompts":[50],"by":[51],"applying":[52,89],"metaoperations,":[53],"defined":[54],"as":[55],"basic":[56],"manipulations":[57],"that":[58,131],"conceal":[59],"harmful":[60],"intent.CDD":[61],"emulates":[62],"human":[63],"cognitive":[64],"reasoning":[65,69],"through":[66],"a":[67,73,82],"structured":[68,94],"chain.It":[70],"begins":[71],"with":[72,81],"global":[74],"perception":[75],"prompt":[78],"follows":[80],"localized":[83],"analysis":[84],"uncover":[86],"hidden":[87],"manipulations.By":[88],"supervised":[90],"fine-tuning":[91],"chain,":[95],"model":[97],"learns":[98],"identify":[100],"reason":[102],"about":[103],"known":[104],"manipulation":[105],"patterns.To":[106],"enhance":[107],"generalization":[108,141],"threats,":[111],"an":[112],"entropy-guided":[113],"reinforcement":[114],"learning":[115],"algorithm":[116],"(EG-GRPO)":[117],"introduced":[119],"encourage":[121],"exploration":[122],"new":[124],"types":[125],"variants":[127],"meta-operations.Experiments":[129],"demonstrate":[130],"CDD":[132],"can":[133],"achieve":[134],"state-of-the-art":[135],"defense":[136],"performance":[137],"exhibit":[139],"strong":[140],"attacks.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2026-07-02T00:00:00"}