{"id":"https://openalex.org/W7156382872","doi":"https://doi.org/10.1145/3774904.3792204","title":"PADD: Prefix-based Attention Divergence Detector for LLM Jailbreaks","display_name":"PADD: Prefix-based Attention Divergence Detector for LLM Jailbreaks","publication_year":2026,"publication_date":"2026-04-12","ids":{"openalex":"https://openalex.org/W7156382872","doi":"https://doi.org/10.1145/3774904.3792204"},"language":null,"primary_location":{"id":"doi:10.1145/3774904.3792204","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792204","pdf_url":null,"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 ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774904.3792204","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059498493","display_name":"Ziqun Bao","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziqun Bao","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0001-0409-2614","affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079319168","display_name":"Jiaqiang Niu","orcid":"https://orcid.org/0000-0003-0377-5672"},"institutions":[{"id":"https://openalex.org/I1328775524","display_name":"Zhejiang Sci-Tech University","ror":"https://ror.org/03893we55","country_code":"CN","type":"education","lineage":["https://openalex.org/I1328775524"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqiang Niu","raw_affiliation_strings":["Zhejiang Sci-Tech University, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0005-8144-3966","affiliations":[{"raw_affiliation_string":"Zhejiang Sci-Tech University, Zhejiang, China","institution_ids":["https://openalex.org/I1328775524"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111278562","display_name":"Yuchen Shao","orcid":null},"institutions":[{"id":"https://openalex.org/I21945476","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89","country_code":"CN","type":"education","lineage":["https://openalex.org/I21945476"]},{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchen Shao","raw_affiliation_strings":["East China Normal University, Shanghai, China and Shanghai Innovation Institute, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0009-0414-7521","affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China and Shanghai Innovation Institute, Shanghai, China","institution_ids":["https://openalex.org/I21945476","https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016446062","display_name":"Chengcheng Wan","orcid":"https://orcid.org/0000-0001-9162-9688"},"institutions":[{"id":"https://openalex.org/I21945476","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89","country_code":"CN","type":"education","lineage":["https://openalex.org/I21945476"]},{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengcheng Wan","raw_affiliation_strings":["East China Normal University, Shanghai, China, China and Shanghai Innovation Institute, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9162-9688","affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China, China and Shanghai Innovation Institute, Shanghai, China","institution_ids":["https://openalex.org/I21945476","https://openalex.org/I66867065"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2683","last_page":"2694"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9538999795913696,"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":0.9538999795913696,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.0066999997943639755,"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":0.005400000140070915,"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/adversarial-system","display_name":"Adversarial system","score":0.6495000123977661},{"id":"https://openalex.org/keywords/evasion","display_name":"Evasion (ethics)","score":0.5486000180244446},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.5249000191688538},{"id":"https://openalex.org/keywords/camouflage","display_name":"Camouflage","score":0.3682999908924103},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.35420000553131104},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.27959999442100525}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6495000123977661},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6021000146865845},{"id":"https://openalex.org/C2781251061","wikidata":"https://www.wikidata.org/wiki/Q5416089","display_name":"Evasion (ethics)","level":3,"score":0.5486000180244446},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5249000191688538},{"id":"https://openalex.org/C2776196576","wikidata":"https://www.wikidata.org/wiki/Q196113","display_name":"Camouflage","level":2,"score":0.3682999908924103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3621000051498413},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.35420000553131104},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.35199999809265137},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C140547941","wikidata":"https://www.wikidata.org/wiki/Q7797194","display_name":"Threat model","level":2,"score":0.2711000144481659}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774904.3792204","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792204","pdf_url":null,"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 ACM Web Conference 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774904.3792204","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792204","pdf_url":null,"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 ACM Web Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W4385573354","https://openalex.org/W4391724817","https://openalex.org/W4401042900","https://openalex.org/W4405181600","https://openalex.org/W4408750038","https://openalex.org/W4410632703"],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"achieved":[5],"remarkable":[6],"progress":[7],"in":[8],"understanding":[9],"and":[10,26,35],"generation":[11,29],"tasks,":[12],"yet":[13],"they":[14],"remain":[15],"highly":[16],"susceptible":[17],"to":[18,52],"adversarial":[19],"prompt":[20,56],"attacks":[21],"that":[22],"bypass":[23],"safety":[24],"safeguards":[25],"induce":[27],"the":[28],"of":[30],"harmful":[31],"content.":[32],"Existing":[33],"pre-generation":[34],"post-generation":[36],"defense":[37],"methods":[38],"typically":[39],"rely":[40],"on":[41],"intent":[42],"recognition,":[43],"surface-level":[44],"features,":[45],"or":[46],"external":[47],"classifiers,":[48],"rendering":[49],"them":[50],"vulnerable":[51],"evasion":[53],"via":[54],"subtle":[55],"perturbations":[57],"while":[58],"incurring":[59],"substantial":[60],"computational":[61],"overhead.":[62]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-04-28T00:00:00"}
