{"id":"https://openalex.org/W7117551250","doi":"https://doi.org/10.1145/3733799.3762981","title":"JailbreaksOverTime: Detecting Jailbreak Attacks Under Distribution Shift","display_name":"JailbreaksOverTime: Detecting Jailbreak Attacks Under Distribution Shift","publication_year":2025,"publication_date":"2025-10-13","ids":{"openalex":"https://openalex.org/W7117551250","doi":"https://doi.org/10.1145/3733799.3762981"},"language":null,"primary_location":{"id":"doi:10.1145/3733799.3762981","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3733799.3762981","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 18th ACM Workshop on Artificial Intelligence and Security","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3733799.3762981","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063198804","display_name":"Julien Piet","orcid":"https://orcid.org/0009-0003-7447-0910"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julien Piet","raw_affiliation_strings":["University of California, Berkeley, Berkeley, USA"],"raw_orcid":"https://orcid.org/0009-0003-7447-0910","affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121547769","display_name":"Xiao Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiao Huang","raw_affiliation_strings":["University of California, Berkeley, Berkeley, USA"],"raw_orcid":"https://orcid.org/0009-0002-5009-8424","affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116053964","display_name":"Dennis Jacob","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dennis Jacob","raw_affiliation_strings":["University of California, Berkeley, Berkeley, USA"],"raw_orcid":"https://orcid.org/0009-0001-9086-8684","affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120625689","display_name":"Annabella Chow","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Annabella Chow","raw_affiliation_strings":["University of California, Berkeley, Berkeley, USA"],"raw_orcid":"https://orcid.org/0000-0002-8494-189X","affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121579799","display_name":"Maha Alrashed","orcid":null},"institutions":[{"id":"https://openalex.org/I1284598098","display_name":"King Abdulaziz City for Science and Technology","ror":"https://ror.org/05tdz6m39","country_code":"SA","type":"facility","lineage":["https://openalex.org/I1284598098"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Maha Alrashed","raw_affiliation_strings":["KACST, Riyadh, Saudi Arabia"],"raw_orcid":"https://orcid.org/0009-0004-5360-1624","affiliations":[{"raw_affiliation_string":"KACST, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I1284598098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102886477","display_name":"Geng Zhao","orcid":"https://orcid.org/0000-0003-0750-356X"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Geng Zhao","raw_affiliation_strings":["University of California, Berkeley, Berkeley, USA"],"raw_orcid":"https://orcid.org/0000-0003-0750-356X","affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051762155","display_name":"Zhanhao Hu","orcid":"https://orcid.org/0000-0002-3746-1447"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhanhao Hu","raw_affiliation_strings":["University of California, Berkeley, Berkeley, USA"],"raw_orcid":"https://orcid.org/0000-0002-3746-1447","affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040461332","display_name":"Chawin Sitawarin","orcid":"https://orcid.org/0000-0002-4949-9661"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chawin Sitawarin","raw_affiliation_strings":["University of California, Berkeley, Berkeley, USA"],"raw_orcid":"https://orcid.org/0000-0002-4949-9661","affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019524943","display_name":"Basel Alomair","orcid":"https://orcid.org/0000-0002-0494-2586"},"institutions":[{"id":"https://openalex.org/I4210096041","display_name":"Riyadh Elm University","ror":"https://ror.org/00rz3mr26","country_code":"SA","type":"education","lineage":["https://openalex.org/I4210096041"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Basel Alomair","raw_affiliation_strings":["KACST, Riyadh, USA"],"raw_orcid":"https://orcid.org/0000-0002-0494-2586","affiliations":[{"raw_affiliation_string":"KACST, Riyadh, USA","institution_ids":["https://openalex.org/I4210096041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121527162","display_name":"David Wagner","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Wagner","raw_affiliation_strings":["University of California, Berkeley, Berkeley, USA"],"raw_orcid":"https://orcid.org/0000-0002-9944-9232","affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"230","last_page":"241"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.78329998254776,"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":0.78329998254776,"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":0.03009999915957451,"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":0.01640000008046627,"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/point","display_name":"Point (geometry)","score":0.49219998717308044},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.3847000002861023},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.3499000072479248},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.34360000491142273},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.3255000114440918},{"id":"https://openalex.org/keywords/system-safety","display_name":"System safety","score":0.3107999861240387}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6732000112533569},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.5162000060081482},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.49219998717308044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4489000141620636},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3847000002861023},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3499000072479248},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.34360000491142273},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3255000114440918},{"id":"https://openalex.org/C132835097","wikidata":"https://www.wikidata.org/wiki/Q7663745","display_name":"System safety","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3091000020503998},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2587999999523163},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3733799.3762981","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3733799.3762981","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 18th ACM Workshop on Artificial Intelligence and Security","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3733799.3762981","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3733799.3762981","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 18th ACM Workshop on Artificial Intelligence and Security","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6023486852645874,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2543927648","https://openalex.org/W3211972406","https://openalex.org/W4383993628","https://openalex.org/W4385714464","https://openalex.org/W4386185470","https://openalex.org/W4387595846","https://openalex.org/W4390632065","https://openalex.org/W4392173735","https://openalex.org/W4393063881","https://openalex.org/W4394007075","https://openalex.org/W4396651342","https://openalex.org/W4398133596","https://openalex.org/W4402217583","https://openalex.org/W4403585381","https://openalex.org/W4405716294","https://openalex.org/W4407093355","https://openalex.org/W4407425033","https://openalex.org/W4407699660","https://openalex.org/W4408612358","https://openalex.org/W4415798831","https://openalex.org/W6892021687"],"related_works":[],"abstract_inverted_index":{"Safety":[0],"and":[1,84],"security":[2],"remain":[3,22],"critical":[4],"concerns":[5],"in":[6,58],"AI":[7],"deployment.":[8],"Despite":[9],"safety":[10,29],"training":[11],"through":[12],"reinforcement":[13],"learning":[14],"with":[15,52],"human":[16],"feedback":[17],"(RLHF)":[18],"[34],":[19],"language":[20],"models":[21],"vulnerable":[23],"to":[24],"jailbreak":[25,46,85],"attacks":[26],"that":[27,33,45,80],"bypass":[28],"guardrails.":[30],"Universal":[31],"jailbreaks\u2014prefixes":[32],"can":[34],"circumvent":[35],"alignment":[36],"for":[37],"any":[38],"payload\u2014are":[39],"particularly":[40],"concerning.":[41],"We":[42],"show":[43],"empirically":[44],"detection":[47],"systems":[48],"face":[49],"distribution":[50],"shift,":[51],"detectors":[53],"trained":[54],"at":[55],"one":[56],"point":[57],"time":[59],"performing":[60],"poorly":[61],"against":[62],"newer":[63],"exploits.":[64],"To":[65],"study":[66],"this":[67],"problem,":[68],"we":[69],"release":[70],"JailbreaksOverTime,":[71],"a":[72],"comprehensive":[73],"dataset":[74],"of":[75,90],"timestamped":[76],"real":[77],"user":[78],"interactions":[79],"contains":[81],"benign":[82],"requests":[83],"attempts":[86],"over":[87],"the":[88],"span":[89],"10":[91],"months.":[92]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-12-30T00:00:00"}
