{"id":"https://openalex.org/W4415535601","doi":"https://doi.org/10.1145/3746027.3755553","title":"MMPro: A Decoupled Perception-Thinking-Execution Framework for Secure GUI Agent","display_name":"MMPro: A Decoupled Perception-Thinking-Execution Framework for Secure GUI Agent","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415535601","doi":"https://doi.org/10.1145/3746027.3755553"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755553","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755553","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","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/A5113311055","display_name":"Benlong Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Benlong Wu","raw_affiliation_strings":["School of Cyber Science and Technology, University of Science and Technology of China, HeFei, China and Key Laboratory of Cyberspace Security, Ministry of Education, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0008-4441-173X","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, University of Science and Technology of China, HeFei, China and Key Laboratory of Cyberspace Security, Ministry of Education, Hefei, China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104186629","display_name":"Yuang Qi","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuang Qi","raw_affiliation_strings":["School of Cyber Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0008-0326-1616","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038253295","display_name":"Xiuwei Shang","orcid":"https://orcid.org/0009-0009-6660-9947"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiuwei Shang","raw_affiliation_strings":["School of Cyber Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0009-6660-9947","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067689180","display_name":"Weiming Zhang","orcid":"https://orcid.org/0000-0001-5576-6108"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiming Zhang","raw_affiliation_strings":["School of Cyber Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-5576-6108","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064573190","display_name":"Nenghai Yu","orcid":"https://orcid.org/0000-0003-4417-9316"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nenghai Yu","raw_affiliation_strings":["School of Cyber Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-4417-9316","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045121980","display_name":"Kejiang Chen","orcid":"https://orcid.org/0000-0002-9868-3414"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kejiang Chen","raw_affiliation_strings":["School of Cyber Science and Technology, University of Science and Technology of China, Hefei, China and Key Laboratory of Cyberspace Security, Ministry of Education, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-9868-3414","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, University of Science and Technology of China, Hefei, China and Key Laboratory of Cyberspace Security, Ministry of Education, Hefei, China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5113311055"],"corresponding_institution_ids":["https://openalex.org/I126520041","https://openalex.org/I16365422"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33745541,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4679","last_page":"4687"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.987500011920929,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.987500011920929,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9847000241279602,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9843999743461609,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/graphical-user-interface","display_name":"Graphical user interface","score":0.690500020980835},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5863999724388123},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.40130001306533813},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.3970000147819519},{"id":"https://openalex.org/keywords/user-interface","display_name":"User interface","score":0.3603000044822693},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.34119999408721924},{"id":"https://openalex.org/keywords/permission","display_name":"Permission","score":0.3142000138759613}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7985000014305115},{"id":"https://openalex.org/C37789001","wikidata":"https://www.wikidata.org/wiki/Q782543","display_name":"Graphical user interface","level":2,"score":0.690500020980835},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5863999724388123},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4661000072956085},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.43369999527931213},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.41690000891685486},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.40130001306533813},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.3970000147819519},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.3603000044822693},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.34119999408721924},{"id":"https://openalex.org/C2779089604","wikidata":"https://www.wikidata.org/wiki/Q7169333","display_name":"Permission","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.313400000333786},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C66153210","wikidata":"https://www.wikidata.org/wiki/Q5597182","display_name":"Graphical user interface testing","level":4,"score":0.29580000042915344},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.27799999713897705},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2727000117301941},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2542000114917755}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755553","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755553","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2017139444","https://openalex.org/W2031332190","https://openalex.org/W2033712349","https://openalex.org/W2740295334","https://openalex.org/W2963518342","https://openalex.org/W4403791736"],"related_works":[],"abstract_inverted_index":{"Advances":[0],"in":[1],"automatic":[2],"graphical":[3],"user":[4],"interface":[5],"(GUI)":[6],"agents":[7],"have":[8],"brought":[9],"significant":[10],"privacy":[11,121],"and":[12,23,50,63,123,137],"security":[13],"challenges,":[14],"especially":[15],"cloud-based":[16],"solutions":[17],"that":[18,41,111],"may":[19],"leak":[20],"sensitive":[21,101],"data":[22],"be":[24],"vulnerable":[25],"to":[26,57,60,71,133],"man-in-the-middle":[27],"attacks.":[28],"To":[29],"address":[30],"these":[31],"issues,":[32],"we":[33],"propose":[34],"MMPro,":[35],"a":[36,43,84,130],"novel":[37],"GUI":[38,77,115,140],"agent":[39,116],"framework":[40],"adopts":[42],"separated":[44],"perception-thinking-execution":[45],"architecture.":[46],"The":[47],"perception":[48],"module":[49,53,66],"the":[51,64,73,76,98,107],"execution":[52],"process":[54],"inputs":[55],"locally":[56],"generate":[58],"outputs":[59],"ensure":[61,72],"security,":[62],"thinking":[65],"operates":[67],"on":[68,106],"abstract":[69,94],"representations":[70],"effectiveness":[74],"of":[75,100],"agent.By":[78],"modularizing":[79],"each":[80],"stage":[81],"while":[82,118],"introducing":[83],"hybrid":[85],"description":[86],"language":[87],"(HDL),":[88],"MMPro":[89,112],"transforms":[90],"screen":[91],"images":[92],"into":[93],"structured":[95],"representations,":[96],"minimizing":[97],"risk":[99],"information":[102],"leakage.":[103],"Experimental":[104],"results":[105],"OSWorld":[108],"benchmark":[109],"show":[110],"outperforms":[113],"existing":[114],"methods":[117],"ensuring":[119],"strong":[120],"protection":[122],"real-time":[124],"interaction":[125],"capabilities.":[126],"This":[127],"work":[128],"presents":[129],"pioneering":[131],"approach":[132],"developing":[134],"efficient,":[135],"privacy-conscious,":[136],"explainable":[138],"automated":[139],"agents.":[141]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-25T00:00:00"}
