{"id":"https://openalex.org/W4413394434","doi":"https://doi.org/10.1109/tmc.2025.3601531","title":"State-Aware Perturbation Optimization for Robust Deep Reinforcement Learning","display_name":"State-Aware Perturbation Optimization for Robust Deep Reinforcement Learning","publication_year":2025,"publication_date":"2025-08-21","ids":{"openalex":"https://openalex.org/W4413394434","doi":"https://doi.org/10.1109/tmc.2025.3601531"},"language":"en","primary_location":{"id":"doi:10.1109/tmc.2025.3601531","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2025.3601531","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Mobile Computing","raw_type":"journal-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":null,"display_name":"Zongyuan Zhang","orcid":"https://orcid.org/0000-0003-4082-2060"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Zongyuan Zhang","raw_affiliation_strings":["Department of Computer Science, University of Hong Kong, Hong Kong, SAR, China","Department of Computer Science, The University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0003-4082-2060","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Hong Kong, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I889458895"]},{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052900159","display_name":"Tianyang Duan","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tianyang Duan","raw_affiliation_strings":["Department of Computer Science, University of Hong Kong, Hong Kong, SAR, China","Department of Computer Science, The University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0009-0006-8044-2176","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Hong Kong, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I889458895"]},{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zheng Lin","orcid":"https://orcid.org/0000-0002-4463-5652"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zheng Lin","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, University of Hong Kong, Hong Kong, SAR, China","Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-4463-5652","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, University of Hong Kong, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I889458895"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Dong Huang","orcid":"https://orcid.org/0000-0002-4275-3006"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Dong Huang","raw_affiliation_strings":["Department of Computer Science, University of Hong Kong, Hong Kong, SAR, China","Department of Computer Science, The University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-4275-3006","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Hong Kong, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I889458895"]},{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057230946","display_name":"Zihan Fang","orcid":"https://orcid.org/0000-0002-0844-9879"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zihan Fang","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China","Department of Computer Science, City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-0844-9879","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zekai Sun","orcid":"https://orcid.org/0000-0003-0269-7940"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zekai Sun","raw_affiliation_strings":["Department of Computer Science, University of Hong Kong, Hong Kong, SAR, China","Department of Computer Science, The University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0003-0269-7940","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Hong Kong, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I889458895"]},{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110378574","display_name":"Ling Xiong","orcid":null},"institutions":[{"id":"https://openalex.org/I102345215","display_name":"Xihua University","ror":"https://ror.org/04gwtvf26","country_code":"CN","type":"education","lineage":["https://openalex.org/I102345215"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ling Xiong","raw_affiliation_strings":["School of Computer and Software Engineering, Xihua University, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0001-9900-2978","affiliations":[{"raw_affiliation_string":"School of Computer and Software Engineering, Xihua University, Chengdu, China","institution_ids":["https://openalex.org/I102345215"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hongbin Liang","orcid":"https://orcid.org/0000-0002-6258-0595"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongbin Liang","raw_affiliation_strings":["National United Engineering Laboratory of Integrated and Intelligent Transportation, Chengdu, China","National United Engineering Laboratory of Integrated and Intelligent Transportation, and the National Engineering Laboratory of Integrated Transportation Big Data Application Technology, Southwest Jiaotong University, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-6258-0595","affiliations":[{"raw_affiliation_string":"National United Engineering Laboratory of Integrated and Intelligent Transportation, Chengdu, China","institution_ids":[]},{"raw_affiliation_string":"National United Engineering Laboratory of Integrated and Intelligent Transportation, and the National Engineering Laboratory of Integrated Transportation Big Data Application Technology, Southwest Jiaotong University, Chengdu, China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015360935","display_name":"Heming Cui","orcid":"https://orcid.org/0000-0001-7746-440X"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Heming Cui","raw_affiliation_strings":["Department of Computer Science, University of Hong Kong, Hong Kong, SAR, China","Department of Computer Science, The University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-7746-440X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Hong Kong, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I889458895"]},{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091090025","display_name":"Yong Cui","orcid":"https://orcid.org/0000-0002-5171-739X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Cui","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5171-739X","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":1.0999,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.80736298,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"25","issue":"1","first_page":"992","last_page":"1008"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14011","display_name":"Elevator Systems and Control","score":0.6841999888420105,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T14011","display_name":"Elevator Systems and Control","score":0.6841999888420105,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.6622999906539917,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6467000246047974,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7912070155143738},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7527745962142944},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43414920568466187}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7912070155143738},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7527745962142944},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43414920568466187}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmc.2025.3601531","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2025.3601531","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Mobile Computing","raw_type":"journal-article"},{"id":"pmh:oai:hub.hku.hk:10722/366578","is_oa":false,"landing_page_url":"http://hdl.handle.net/10722/366578","pdf_url":null,"source":{"id":"https://openalex.org/S4377196271","display_name":"The HKU Scholars Hub (University of Hong Kong)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I889458895","host_organization_name":"University of Hong Kong","host_organization_lineage":["https://openalex.org/I889458895"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","score":0.41999998688697815,"display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2150468603","https://openalex.org/W2774644650","https://openalex.org/W2779458783","https://openalex.org/W2941205169","https://openalex.org/W2951360122","https://openalex.org/W2962847335","https://openalex.org/W2969542116","https://openalex.org/W3127807678","https://openalex.org/W3164563754","https://openalex.org/W3200885897","https://openalex.org/W3202281277","https://openalex.org/W3206227555","https://openalex.org/W3211999566","https://openalex.org/W4214717370","https://openalex.org/W4362672763","https://openalex.org/W4365421095","https://openalex.org/W4378194871","https://openalex.org/W4385061644","https://openalex.org/W4388819705","https://openalex.org/W4390738588","https://openalex.org/W4392173003","https://openalex.org/W4403422358","https://openalex.org/W4408354938"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2138720691","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Recently,":[0],"deep":[1],"reinforcement":[2,105],"learning":[3],"(DRL)":[4],"has":[5],"emerged":[6],"as":[7],"a":[8,69,94,102,122,155],"promising":[9],"approach":[10],"for":[11,55,93,167],"robotic":[12],"control.":[13],"However,":[14],"the":[15,63,79,88,161],"deployment":[16],"of":[17,72],"DRL":[18,49,76],"in":[19,75],"real-world":[20],"robots":[21],"is":[22],"hindered":[23],"by":[24,77],"its":[25],"sensitivity":[26],"to":[27,47,53,86,111,127,143],"environmental":[28,149],"perturbations.":[29],"While":[30],"existing":[31],"whitebox":[32],"adversarial":[33,80,106],"attacks":[34,74],"rely":[35],"on":[36,98],"local":[37],"gradient":[38],"information":[39,146],"and":[40,58,90,115,133,151],"apply":[41],"uniform":[42],"perturbations":[43],"across":[44],"all":[45],"states":[46,166],"evaluate":[48],"robustness,":[50],"they":[51],"fail":[52],"account":[54],"temporal":[56],"dynamics":[57],"statespecific":[59],"vulnerabilities.":[60],"To":[61],"combat":[62],"above":[64],"challenge,":[65],"we":[66,100],"first":[67,120],"conduct":[68],"theoretical":[70],"analysis":[71],"white-box":[73],"establishing":[78],"victim-dynamics":[81],"Markov":[82],"decision":[83],"process":[84],"(AVD-MDP),":[85],"derive":[87],"necessary":[89],"sufficient":[91],"conditions":[92],"successful":[95],"attack.":[96],"Based":[97],"this,":[99],"propose":[101],"selective":[103],"state-aware":[104],"attack":[107,134],"method,":[108],"named":[109],"STAR,":[110],"optimize":[112],"perturbation":[113],"stealthiness":[114,132],"state":[116],"visitation":[117],"dispersion.":[118],"STAR":[119,175],"employs":[121],"soft":[123],"mask-based":[124],"state-targeting":[125],"mechanism":[126],"minimize":[128],"redundant":[129],"perturbations,":[130,148],"enhancing":[131],"effectiveness.":[135],"Then,":[136],"it":[137],"incorporates":[138],"an":[139],"information-theoretic":[140],"optimization":[141],"objective":[142],"maximize":[144],"mutual":[145],"between":[147],"states,":[150],"victim":[152,162],"actions,":[153],"ensuring":[154],"dispersed":[156],"state-visitation":[157],"distribution":[158],"that":[159,174],"steers":[160],"agent":[163],"into":[164],"vulnerable":[165],"maximum":[168],"return":[169],"reduction.":[170],"Extensive":[171],"experiments":[172],"demonstrate":[173],"outperforms":[176],"state-of-the-art":[177],"benchmarks":[178]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}