{"id":"https://openalex.org/W4408354938","doi":"https://doi.org/10.1109/icassp49660.2025.10890540","title":"Rethinking Adversarial Attacks in Reinforcement Learning from Policy Distribution Perspective","display_name":"Rethinking Adversarial Attacks in Reinforcement Learning from Policy Distribution Perspective","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354938","doi":"https://doi.org/10.1109/icassp49660.2025.10890540"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890540","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890540","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/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":true,"raw_author_name":"Tianyang Duan","raw_affiliation_strings":["The University of Hong Kong,Department of Computer Science,Hong Kong,China"],"affiliations":[{"raw_affiliation_string":"The University of Hong Kong,Department of Computer Science,Hong Kong,China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080465399","display_name":"Zongyuan Zhang","orcid":"https://orcid.org/0000-0003-4577-2613"},"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":"Zongyuan Zhang","raw_affiliation_strings":["The University of Hong Kong,Department of Computer Science,Hong Kong,China"],"affiliations":[{"raw_affiliation_string":"The University of Hong Kong,Department of Computer Science,Hong Kong,China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052137404","display_name":"Lin Zheng","orcid":"https://orcid.org/0000-0003-0351-4827"},"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":["The University of Hong Kong,Department of Electrical and Electronic Engineering,Hong Kong,China"],"affiliations":[{"raw_affiliation_string":"The University of Hong Kong,Department of Electrical and Electronic Engineering,Hong Kong,China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100602494","display_name":"Yue Gao","orcid":"https://orcid.org/0000-0002-4971-590X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Gao","raw_affiliation_strings":["Fudan University,School of Computer Science,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science,China","institution_ids":["https://openalex.org/I24943067"]}]},{"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":["Xihua University,School of Computer and Software Engineering,Chengdu,China"],"affiliations":[{"raw_affiliation_string":"Xihua University,School of Computer and Software Engineering,Chengdu,China","institution_ids":["https://openalex.org/I102345215"]}]},{"author_position":"middle","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":["Tsinghua University,Department of Computer Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100784667","display_name":"H. Liang","orcid":"https://orcid.org/0000-0002-3972-2049"},"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":["Southwest Jiaotong University,School of Transportation and Logistics,Chengdu,China"],"affiliations":[{"raw_affiliation_string":"Southwest Jiaotong University,School of Transportation and Logistics,Chengdu,China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046390476","display_name":"Xianhao Chen","orcid":"https://orcid.org/0009-0001-7031-1440"},"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":"Xianhao Chen","raw_affiliation_strings":["The University of Hong Kong,Department of Electrical and Electronic Engineering,Hong Kong,China"],"affiliations":[{"raw_affiliation_string":"The University of Hong Kong,Department of Electrical and Electronic Engineering,Hong Kong,China","institution_ids":["https://openalex.org/I889458895"]}]},{"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":["The University of Hong Kong,Department of Computer Science,Hong Kong,China"],"affiliations":[{"raw_affiliation_string":"The University of Hong Kong,Department of Computer Science,Hong Kong,China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100308056","display_name":"Dong Huang","orcid":"https://orcid.org/0000-0001-9715-6922"},"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":["The University of Hong Kong,Department of Computer Science,Hong Kong,China"],"affiliations":[{"raw_affiliation_string":"The University of Hong Kong,Department of Computer Science,Hong Kong,China","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5052900159"],"corresponding_institution_ids":["https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":3.5516,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.91891892,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.33739998936653137,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.33739998936653137,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.32409998774528503,"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/T14053","display_name":"Dengue and Mosquito Control Research","score":0.32190001010894775,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.917346715927124},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7715029120445251},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.7425642609596252},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6400749087333679},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.49962782859802246},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.46375730633735657},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.4156016707420349},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35593515634536743},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11273115873336792},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10282129049301147},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.0942370593547821}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.917346715927124},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7715029120445251},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.7425642609596252},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6400749087333679},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.49962782859802246},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.46375730633735657},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.4156016707420349},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35593515634536743},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11273115873336792},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10282129049301147},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0942370593547821},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890540","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890540","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1904826605","https://openalex.org/W2149197198","https://openalex.org/W2541678333","https://openalex.org/W2765424254","https://openalex.org/W2774644650","https://openalex.org/W2941205169","https://openalex.org/W2962847335","https://openalex.org/W2964152294","https://openalex.org/W2997293639","https://openalex.org/W3013520104","https://openalex.org/W3022324591","https://openalex.org/W3027406032","https://openalex.org/W3135970545","https://openalex.org/W3158253560","https://openalex.org/W3216283008","https://openalex.org/W4214717370","https://openalex.org/W4297964528","https://openalex.org/W4303649662","https://openalex.org/W4316035622","https://openalex.org/W4382237537","https://openalex.org/W4386432124","https://openalex.org/W4390871715","https://openalex.org/W6638018090","https://openalex.org/W6640425456","https://openalex.org/W6733049761","https://openalex.org/W6737893269","https://openalex.org/W6739868092","https://openalex.org/W6747027214","https://openalex.org/W6754762128","https://openalex.org/W6759129252","https://openalex.org/W6768366551","https://openalex.org/W6770271268","https://openalex.org/W6771690906","https://openalex.org/W6774966973","https://openalex.org/W6777834836","https://openalex.org/W6781541518","https://openalex.org/W6789484704","https://openalex.org/W6796690604","https://openalex.org/W6809338775","https://openalex.org/W6858013149"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4310988119","https://openalex.org/W4285226279"],"abstract_inverted_index":{"Deep":[0],"Reinforcement":[1],"Learning":[2],"(DRL)":[3],"suffers":[4],"from":[5],"uncertainties":[6],"and":[7],"inaccuracies":[8],"in":[9,13,46,94,124],"the":[10,24,41,56,68,74,79,91,122,138],"observation":[11],"signal":[12],"real-world":[14],"applications.":[15],"Adversarial":[16],"attack":[17,31,61,73],"is":[18],"an":[19,130],"effective":[20],"method":[21],"for":[22],"evaluating":[23],"robustness":[25],"of":[26,103],"DRL":[27],"agents.":[28],"However,":[29],"existing":[30],"methods":[32],"targeting":[33],"individual":[34,87],"sampled":[35],"actions":[36],"have":[37],"limited":[38],"impacts":[39],"on":[40,86],"overall":[42],"policy":[43,75,81,98],"distribution,":[44],"particularly":[45],"continuous":[47],"action":[48],"spaces.":[49],"To":[50],"address":[51],"these":[52],"limitations,":[53],"we":[54],"propose":[55],"Distribution-Aware":[57],"Projected":[58],"Gradient":[59],"Descent":[60],"(DAPGD).":[62],"DAPGD":[63,95,116],"uses":[64],"distribution":[65,82],"similarity":[66],"as":[67],"gradient":[69],"perturbation":[70],"input":[71],"to":[72,96,121,137],"network,":[76],"which":[77],"leverages":[78],"entire":[80],"rather":[83],"than":[84],"relying":[85],"samples.":[88],"We":[89],"utilize":[90],"Bhattacharyya":[92],"distance":[93],"measure":[97],"similarity,":[99],"enabling":[100],"sensitive":[101],"detection":[102],"subtle":[104],"but":[105],"critical":[106],"differences":[107],"between":[108],"probability":[109],"distributions.":[110],"Our":[111],"experiment":[112],"results":[113,119],"demonstrate":[114],"that":[115],"achieves":[117],"SOTA":[118],"compared":[120,136],"baselines":[123],"three":[125],"robot":[126],"navigation":[127],"tasks,":[128],"achieving":[129],"average":[131],"22.03%":[132],"higher":[133],"reward":[134],"drop":[135],"best":[139],"baseline.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}