{"id":"https://openalex.org/W4415091277","doi":"https://doi.org/10.1007/978-3-032-07884-1_13","title":"Countering Jailbreak Attacks with\u00a0Two-Axis Pre-detection and\u00a0Conditional Warning Wrappers","display_name":"Countering Jailbreak Attacks with\u00a0Two-Axis Pre-detection and\u00a0Conditional Warning Wrappers","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4415091277","doi":"https://doi.org/10.1007/978-3-032-07884-1_13"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-032-07884-1_13","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-032-07884-1_13","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5086270065","display_name":"Hyunsik Na","orcid":"https://orcid.org/0000-0002-7123-4467"},"institutions":[{"id":"https://openalex.org/I141371507","display_name":"Soongsil University","ror":"https://ror.org/017xnm587","country_code":"KR","type":"education","lineage":["https://openalex.org/I141371507"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Hyunsik Na","raw_affiliation_strings":["Soongsil University, Seoul, 06978, South Korea"],"affiliations":[{"raw_affiliation_string":"Soongsil University, Seoul, 06978, South Korea","institution_ids":["https://openalex.org/I141371507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003168385","display_name":"Hajun Kim","orcid":"https://orcid.org/0009-0002-9430-7830"},"institutions":[{"id":"https://openalex.org/I141371507","display_name":"Soongsil University","ror":"https://ror.org/017xnm587","country_code":"KR","type":"education","lineage":["https://openalex.org/I141371507"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hajun Kim","raw_affiliation_strings":["Soongsil University, Seoul, 06978, South Korea"],"affiliations":[{"raw_affiliation_string":"Soongsil University, Seoul, 06978, South Korea","institution_ids":["https://openalex.org/I141371507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041435353","display_name":"Daekeun Yoon","orcid":"https://orcid.org/0000-0003-4527-3603"},"institutions":[{"id":"https://openalex.org/I4210110138","display_name":"Koh Young Technology (South Korea)","ror":"https://ror.org/0244stc74","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210110138"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dooshik Yoon","raw_affiliation_strings":["eRoun&Company Co., Ltd., Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"eRoun&Company Co., Ltd., Seoul, South Korea","institution_ids":["https://openalex.org/I4210110138"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053797473","display_name":"Daeseon Choi","orcid":"https://orcid.org/0000-0002-1438-0265"},"institutions":[{"id":"https://openalex.org/I141371507","display_name":"Soongsil University","ror":"https://ror.org/017xnm587","country_code":"KR","type":"education","lineage":["https://openalex.org/I141371507"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Daeseon Choi","raw_affiliation_strings":["Soongsil University, Seoul, 06978, South Korea"],"affiliations":[{"raw_affiliation_string":"Soongsil University, Seoul, 06978, South Korea","institution_ids":["https://openalex.org/I141371507"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5086270065"],"corresponding_institution_ids":["https://openalex.org/I141371507"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.47445234,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"249","last_page":"268"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9993000030517578,"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":0.9993000030517578,"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":0.996999979019165,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/false-positive-paradox","display_name":"False positive paradox","score":0.8447999954223633},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.829200029373169},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.6074000000953674},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5266000032424927},{"id":"https://openalex.org/keywords/adversarial-machine-learning","display_name":"Adversarial machine learning","score":0.44999998807907104},{"id":"https://openalex.org/keywords/false-positives-and-false-negatives","display_name":"False positives and false negatives","score":0.3928999900817871},{"id":"https://openalex.org/keywords/warning-system","display_name":"Warning system","score":0.375}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8878999948501587},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.8447999954223633},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.829200029373169},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.6074000000953674},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5266000032424927},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.5077000260353088},{"id":"https://openalex.org/C2778403875","wikidata":"https://www.wikidata.org/wiki/Q20312394","display_name":"Adversarial machine learning","level":3,"score":0.44999998807907104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40860000252723694},{"id":"https://openalex.org/C112789634","wikidata":"https://www.wikidata.org/wiki/Q18207010","display_name":"False positives and false negatives","level":3,"score":0.3928999900817871},{"id":"https://openalex.org/C29825287","wikidata":"https://www.wikidata.org/wiki/Q1427940","display_name":"Warning system","level":2,"score":0.375},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3467000126838684},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3312000036239624},{"id":"https://openalex.org/C2989486834","wikidata":"https://www.wikidata.org/wiki/Q3808900","display_name":"True positive rate","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C59577422","wikidata":"https://www.wikidata.org/wiki/Q10265143","display_name":"False accusation","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C95922358","wikidata":"https://www.wikidata.org/wiki/Q5432725","display_name":"False positive rate","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C65856478","wikidata":"https://www.wikidata.org/wiki/Q3991682","display_name":"Attack model","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2818000018596649}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-032-07884-1_13","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-032-07884-1_13","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2144211451","https://openalex.org/W2963351448","https://openalex.org/W3100355250","https://openalex.org/W4379801086","https://openalex.org/W4382318449","https://openalex.org/W4385570854","https://openalex.org/W4386693657","https://openalex.org/W4389519291","https://openalex.org/W4389617257","https://openalex.org/W4396685186","https://openalex.org/W4399254260","https://openalex.org/W4401042550","https://openalex.org/W4401042699","https://openalex.org/W4401043204","https://openalex.org/W4402670748","https://openalex.org/W4402670895","https://openalex.org/W4402671039","https://openalex.org/W4402671137","https://openalex.org/W4405181600","https://openalex.org/W4405183113","https://openalex.org/W4411010518","https://openalex.org/W6974364291"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-13T00:00:00"}