{"id":"https://openalex.org/W7162082447","doi":"https://doi.org/10.1145/3786335.3813173","title":"Does Safety Molt? Evaluating LLM Safety in Multi-Agent Social Environments","display_name":"Does Safety Molt? Evaluating LLM Safety in Multi-Agent Social Environments","publication_year":2026,"publication_date":"2026-05-22","ids":{"openalex":"https://openalex.org/W7162082447","doi":"https://doi.org/10.1145/3786335.3813173"},"language":null,"primary_location":{"id":"doi:10.1145/3786335.3813173","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786335.3813173","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 Conference on AI and Agentic Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3786335.3813173","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048841872","display_name":"Aman Priyanshu","orcid":"https://orcid.org/0000-0001-6985-9575"},"institutions":[{"id":"https://openalex.org/I151281966","display_name":"Cisco Systems (China)","ror":"https://ror.org/02qy75381","country_code":"CN","type":"company","lineage":["https://openalex.org/I135428043","https://openalex.org/I151281966"]},{"id":"https://openalex.org/I4210129566","display_name":"Cisco Systems (United States)","ror":null,"country_code":"US","type":null,"lineage":["https://openalex.org/I4210129566"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Aman Priyanshu","raw_affiliation_strings":["Cisco Systems Inc., Foundation-AI, San Francisco, California, USA"],"raw_orcid":"https://orcid.org/0000-0001-6985-9575","affiliations":[{"raw_affiliation_string":"Cisco Systems Inc., Foundation-AI, San Francisco, California, USA","institution_ids":["https://openalex.org/I4210129566","https://openalex.org/I151281966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031832389","display_name":"Supriti Vijay","orcid":null},"institutions":[{"id":"https://openalex.org/I151281966","display_name":"Cisco Systems (China)","ror":"https://ror.org/02qy75381","country_code":"CN","type":"company","lineage":["https://openalex.org/I135428043","https://openalex.org/I151281966"]},{"id":"https://openalex.org/I4210129566","display_name":"Cisco Systems (United States)","ror":null,"country_code":"US","type":null,"lineage":["https://openalex.org/I4210129566"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Supriti Vijay","raw_affiliation_strings":["Cisco Systems Inc., Foundation-AI, San Francisco, California, USA"],"raw_orcid":"https://orcid.org/0009-0007-8746-1932","affiliations":[{"raw_affiliation_string":"Cisco Systems Inc., Foundation-AI, San Francisco, California, USA","institution_ids":["https://openalex.org/I4210129566","https://openalex.org/I151281966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5136798658","display_name":"Esha Pahwa","orcid":"https://orcid.org/0009-0005-9697-7864"},"institutions":[{"id":"https://openalex.org/I4210154861","display_name":"Open Medicine Institute","ror":"https://ror.org/050p5yf06","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210154861"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Esha Pahwa","raw_affiliation_strings":["Corvic AI, Mountain View, California, USA"],"raw_orcid":"https://orcid.org/0009-0005-9697-7864","affiliations":[{"raw_affiliation_string":"Corvic AI, Mountain View, California, USA","institution_ids":["https://openalex.org/I4210154861"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.81362698,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"727","last_page":"737"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.26489999890327454,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.26489999890327454,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11045","display_name":"Privacy, Security, and Data Protection","score":0.0885000005364418,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.05920000001788139,"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":0.4738999903202057},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.3799999952316284},{"id":"https://openalex.org/keywords/information-privacy","display_name":"Information privacy","score":0.3149999976158142},{"id":"https://openalex.org/keywords/information-sensitivity","display_name":"Information sensitivity","score":0.27300000190734863},{"id":"https://openalex.org/keywords/information-leakage","display_name":"Information leakage","score":0.26570001244544983}],"concepts":[{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.5138000249862671},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.4894999861717224},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.47679999470710754},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4738999903202057},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4519999921321869},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.3799999952316284},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.3531000018119812},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.3149999976158142},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2948000133037567},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2842999994754791},{"id":"https://openalex.org/C137822555","wikidata":"https://www.wikidata.org/wiki/Q2587068","display_name":"Information sensitivity","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C2779201187","wikidata":"https://www.wikidata.org/wiki/Q2775060","display_name":"Information leakage","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C2777042071","wikidata":"https://www.wikidata.org/wiki/Q6509304","display_name":"Leakage (economics)","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C39549134","wikidata":"https://www.wikidata.org/wiki/Q133080","display_name":"Public relations","level":1,"score":0.25450000166893005},{"id":"https://openalex.org/C110379092","wikidata":"https://www.wikidata.org/wiki/Q1571836","display_name":"Social environment","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3786335.3813173","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786335.3813173","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 Conference on AI and Agentic Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3786335.3813173","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786335.3813173","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 Conference on AI and Agentic Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6366432905197144}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1967317786","https://openalex.org/W1968444823","https://openalex.org/W2207884471","https://openalex.org/W4283172211","https://openalex.org/W4385894687","https://openalex.org/W4387835442","https://openalex.org/W4388886073","https://openalex.org/W4410358178","https://openalex.org/W4415800797","https://openalex.org/W7116746165","https://openalex.org/W7133239970","https://openalex.org/W7134979870"],"related_works":[],"abstract_inverted_index":{"LLM":[0,30],"safety":[1,48,127],"evaluations":[2,149],"predominantly":[3],"test":[4],"models":[5],"in":[6,132],"isolation,":[7],"yet":[8],"deployed":[9],"AI":[10],"agents":[11,31,85],"increasingly":[12],"operate":[13],"within":[14],"persistent":[15],"social":[16,54,66,137],"environments":[17],"alongside":[18],"other":[19],"agents.":[20],"We":[21,56],"introduce":[22],"a":[23,36,46,96],"Moltbook-style":[24],"simulation":[25],"platform":[26],"where":[27],"thousands":[28],"of":[29,53],"interact":[32],"across":[33,76],"communities":[34],"over":[35],"simulated":[37],"month,":[38],"and":[39,100,135],"use":[40],"it":[41],"to":[42,63,73,90,142],"evaluate":[43],"privacy":[44,69,103],"as":[45],"downstream":[47],"concern":[49],"under":[50],"varying":[51],"degrees":[52],"pressure.":[55],"find":[57],"that":[58,79,101,123,136,146],"shifting":[59],"from":[60],"single":[61,147],"turn":[62,65,148],"multi":[64],"evaluation":[67],"amplifies":[68],"violations":[70],"(CIMemories":[71],"19.95%":[72],"Ours":[74],"45.30%":[75],"OpenAI":[77],"models),":[78],"leakage":[80,113],"is":[81,140],"socially":[82],"contagious,":[83],"with":[84,118],"8":[86],"\u00d7":[87],"more":[88],"likely":[89],"disclose":[91],"sensitive":[92,144],"information":[93],"after":[94],"observing":[95],"peer":[97],"do":[98,107],"so,":[99],"explicit":[102],"instructions":[104],"reduce":[105],"but":[106],"not":[108],"eliminate":[109],"this":[110],"effect,":[111],"leaving":[112],"rates":[114],"above":[115],"37.8%":[116],"even":[117],"safeguards.":[119],"Our":[120],"findings":[121],"suggest":[122],"static":[124],"chat":[125],"based":[126],"benchmarks":[128],"systematically":[129],"underestimate":[130],"risks":[131],"agentic":[133],"deployment,":[134],"context":[138],"alone":[139],"sufficient":[141],"elicit":[143],"disclosures":[145],"would":[150],"never":[151],"surface.":[152]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-23T00:00:00"}
