{"id":"https://openalex.org/W4416034129","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1249","title":"MOCHA: Are Code Language Models Robust Against Multi-Turn Malicious Coding Prompts?","display_name":"MOCHA: Are Code Language Models Robust Against Multi-Turn Malicious Coding Prompts?","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034129","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1249"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1249","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1249","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1249.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.1249.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086474262","display_name":"Muntasir Wahed","orcid":"https://orcid.org/0000-0002-9948-023X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Muntasir Wahed","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004900217","display_name":"Xiaona Zhou","orcid":"https://orcid.org/0000-0001-5101-6780"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaona Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Kiet A. Nguyen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kiet A. Nguyen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032986065","display_name":"Tianjiao Yu","orcid":"https://orcid.org/0000-0002-2530-9296"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianjiao Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118212500","display_name":"Nirav Diwan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nirav Diwan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100367403","display_name":"Gang Wang","orcid":"https://orcid.org/0000-0002-7266-2412"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gang Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113822366","display_name":"Dilek Hakkani-T\u00fcr","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dilek Hakkani-T\u00fcr","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5043962698","display_name":"Ismini Lourentzou","orcid":"https://orcid.org/0000-0002-1238-772X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ismini Lourentzou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29743659,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22922","last_page":"22948"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.249099999666214,"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":0.249099999666214,"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":0.05689999833703041,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.0430000014603138,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4756999909877777},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4117000102996826},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.3328999876976013},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.32670000195503235},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.32010000944137573}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6833000183105469},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4756999909877777},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4117000102996826},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3359000086784363},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.32670000195503235},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3147999942302704},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29100000858306885},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2904999852180481},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2766000032424927},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25690001249313354},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1249","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1249","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1249.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1249","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1249","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1249.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034129.pdf","grobid_xml":"https://content.openalex.org/works/W4416034129.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,76,103,122],"LLMs":[3],"have":[4],"significantly":[5],"enhanced":[6],"code":[7,22],"generation.However,":[8],"their":[9],"robustness":[10,87],"against":[11],"multi-turn":[12,59,77],"malicious":[13,27],"coding":[14,28,61,90],"jailbreaks":[15],"remains":[16],"underexplored.In":[17],"this":[18],"work,":[19],"we":[20,49],"introduce":[21],"decomposition":[23],"attacks,":[24],"where":[25,79],"a":[26,33,52,114,128],"task":[29],"is":[30],"disguised":[31],"as":[32],"sequence":[34],"of":[35,55,116,131],"benign":[36],"subtasks":[37],"across":[38],"multiple":[39],"conversational":[40],"turns":[41],"to":[42,94,100],"bypass":[43],"safety":[44],"filters.To":[45],"facilitate":[46],"systematic":[47],"evaluation,":[48],"curate":[50],"MOCHA,":[51],"large-scale":[53],"benchmark":[54],"10K":[56],"single-turn":[57],"and":[58,92],"jailbreak":[60],"prompts":[62],"spanning":[63],"13":[64],"real-world":[65],"threat":[66],"categories.Experiments":[67],"on":[68,84],"open-and":[69],"closedsource":[70],"models":[71],"reveal":[72],"persistent":[73],"vulnerabilities,":[74],"particularly":[75],"settings":[78],"rejection":[80,104],"rates":[81,105],"drop":[82],"sharply.Fine-tuning":[83],"MOCHA":[85],"improves":[86],"while":[88],"preserving":[89],"ability,":[91],"generalizes":[93],"external":[95],"adversarial":[96],"datasets,":[97],"yielding":[98],"up":[99],"32.4%":[101],"increase":[102],"without":[106],"additional":[107],"supervision.*":[108],"This":[109],"paper":[110],"was":[111],"developed":[112],"by":[113],"subset":[115],"the":[117,123,132,137],"UIUC":[118],"team":[119,134],"that":[120],"participated":[121],"Amazon":[124,139],"NOVA":[125],"AI":[126],"Challenge.For":[127],"comprehensive":[129],"account":[130],"full":[133],"effort,":[135],"see":[136],"accompanying":[138],"technical":[140],"report":[141],"(Liu":[142],"et":[143],"al.,":[144],"2025a).":[145]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-08T00:00:00"}