{"id":"https://openalex.org/W3007869767","doi":"https://doi.org/10.1109/tcds.2020.2974509","title":"Minimalistic Attacks: How Little It Takes to Fool Deep Reinforcement Learning Policies","display_name":"Minimalistic Attacks: How Little It Takes to Fool Deep Reinforcement Learning Policies","publication_year":2020,"publication_date":"2020-02-19","ids":{"openalex":"https://openalex.org/W3007869767","doi":"https://doi.org/10.1109/tcds.2020.2974509","mag":"3007869767"},"language":"en","primary_location":{"id":"doi:10.1109/tcds.2020.2974509","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2020.2974509","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Cognitive and Developmental Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://dr.ntu.edu.sg/bitstream/10356/153700/2/Minimalistic%20Attacks%20in%20DRL.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048340011","display_name":"Xinghua Qu","orcid":"https://orcid.org/0000-0001-8072-2019"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xinghua Qu","raw_affiliation_strings":["Computational Intelligence Lab, School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-8072-2019","affiliations":[{"raw_affiliation_string":"Computational Intelligence Lab, School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033957641","display_name":"Zhu Sun","orcid":"https://orcid.org/0000-0002-3350-7022"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhu Sun","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-3350-7022","affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068243197","display_name":"Yew-Soon Ong","orcid":"https://orcid.org/0000-0002-4480-169X"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yew-Soon Ong","raw_affiliation_strings":["A*STAR Initiative for AI & Analytics Innovation, Agency for Science, Technology and Research, Singapore","Data Science and Artificial Intelligence Research Centre, School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4480-169X","affiliations":[{"raw_affiliation_string":"A*STAR Initiative for AI & Analytics Innovation, Agency for Science, Technology and Research, Singapore","institution_ids":["https://openalex.org/I115228651"]},{"raw_affiliation_string":"Data Science and Artificial Intelligence Research Centre, School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041091856","display_name":"Abhishek Gupta","orcid":"https://orcid.org/0000-0002-6080-855X"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I4210091207","display_name":"Singapore Institute of Manufacturing Technology","ror":"https://ror.org/00f44np30","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I4210091207","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Abhishek Gupta","raw_affiliation_strings":["Singapore Institute of Manufacturing Technology, A*STAR, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Institute of Manufacturing Technology, A*STAR, Singapore","institution_ids":["https://openalex.org/I4210091207","https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101506669","display_name":"Pengfei Wei","orcid":"https://orcid.org/0000-0001-8093-0803"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Pengfei Wei","raw_affiliation_strings":["Department of Computer Science, National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3853,"has_fulltext":true,"cited_by_count":41,"citation_normalized_percentile":{"value":0.93639908,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"13","issue":"4","first_page":"806","last_page":"817"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":1.0,"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":1.0,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9883999824523926,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9611999988555908,"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/computer-science","display_name":"Computer science","score":0.7341867089271545},{"id":"https://openalex.org/keywords/adversary","display_name":"Adversary","score":0.673897922039032},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5750357508659363},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5613847970962524},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5340188145637512},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5213407278060913},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.49784207344055176},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.42950859665870667},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.3301667869091034},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3010725975036621}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7341867089271545},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.673897922039032},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5750357508659363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5613847970962524},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5340188145637512},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5213407278060913},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.49784207344055176},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.42950859665870667},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3301667869091034},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3010725975036621}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcds.2020.2974509","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2020.2974509","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Cognitive and Developmental Systems","raw_type":"journal-article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/153700","is_oa":true,"landing_page_url":"https://hdl.handle.net/10356/153700","pdf_url":"https://dr.ntu.edu.sg/bitstream/10356/153700/2/Minimalistic%20Attacks%20in%20DRL.pdf","source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"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":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:dr.ntu.edu.sg:10356/153700","is_oa":true,"landing_page_url":"https://hdl.handle.net/10356/153700","pdf_url":"https://dr.ntu.edu.sg/bitstream/10356/153700/2/Minimalistic%20Attacks%20in%20DRL.pdf","source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"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":"Journal Article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7599999904632568}],"awards":[{"id":"https://openalex.org/G1695904222","display_name":null,"funder_award_id":"AISG-RP-2018-004","funder_id":"https://openalex.org/F4320320766","funder_display_name":"Nanyang Technological University"},{"id":"https://openalex.org/G6796518941","display_name":null,"funder_award_id":"AISG-RP-2018-004","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"}],"funders":[{"id":"https://openalex.org/F4320317988","display_name":"Artificial Intelligence Research Center","ror":null},{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320320766","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302"},{"id":"https://openalex.org/F4320336864","display_name":"Data Science and Artificial Intelligence Research Centre, Nanyang Technological University","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3007869767.pdf","grobid_xml":"https://content.openalex.org/works/W3007869767.grobid-xml"},"referenced_works_count":63,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1673923490","https://openalex.org/W1757796397","https://openalex.org/W1771410628","https://openalex.org/W1945616565","https://openalex.org/W1970127232","https://openalex.org/W1994867044","https://openalex.org/W2012451526","https://openalex.org/W2032100464","https://openalex.org/W2035003264","https://openalex.org/W2040734884","https://openalex.org/W2073258676","https://openalex.org/W2101097701","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2156106639","https://openalex.org/W2166739626","https://openalex.org/W2257979135","https://openalex.org/W2586101872","https://openalex.org/W2595502370","https://openalex.org/W2602963933","https://openalex.org/W2605924076","https://openalex.org/W2616650140","https://openalex.org/W2616841723","https://openalex.org/W2619989803","https://openalex.org/W2736601468","https://openalex.org/W2746600820","https://openalex.org/W2749928749","https://openalex.org/W2765424254","https://openalex.org/W2766447205","https://openalex.org/W2767471303","https://openalex.org/W2770695371","https://openalex.org/W2773525213","https://openalex.org/W2793066534","https://openalex.org/W2798766386","https://openalex.org/W2891186800","https://openalex.org/W2904250082","https://openalex.org/W2910821988","https://openalex.org/W2911506106","https://openalex.org/W2941205169","https://openalex.org/W2947638559","https://openalex.org/W2949103145","https://openalex.org/W2950829764","https://openalex.org/W2963178695","https://openalex.org/W2963207607","https://openalex.org/W2963389226","https://openalex.org/W2964043796","https://openalex.org/W2964108292","https://openalex.org/W2964153729","https://openalex.org/W2968800863","https://openalex.org/W2969419629","https://openalex.org/W3103557498","https://openalex.org/W3106412272","https://openalex.org/W4250503569","https://openalex.org/W4250739957","https://openalex.org/W4298857966","https://openalex.org/W6638018090","https://openalex.org/W6692846177","https://openalex.org/W6735677848","https://openalex.org/W6743802245","https://openalex.org/W6745993369","https://openalex.org/W6747027214","https://openalex.org/W6763848914"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W4246396837","https://openalex.org/W4320018150","https://openalex.org/W2918664383","https://openalex.org/W2040808657","https://openalex.org/W3176659669","https://openalex.org/W4320855730","https://openalex.org/W3123119822","https://openalex.org/W106056076","https://openalex.org/W2135200719"],"abstract_inverted_index":{"Recent":[0],"studies":[1],"have":[2],"revealed":[3],"that":[4],"neural-network-based":[5],"policies":[6,168],"can":[7],"be":[8,130],"easily":[9],"fooled":[10],"by":[11,61,137,151,173,186,191],"adversarial":[12,135],"examples.":[13],"However,":[14],"while":[15],"most":[16],"prior":[17],"works":[18],"analyze":[19],"the":[20,45,49,77,83,107,134,139,178,183],"effects":[21],"of":[22,26,47,51,90,177],"perturbing":[23,192],"every":[24,27],"pixel":[25],"frame":[28],"assuming":[29],"white-box":[30],"policy":[31,184],"access,":[32],"in":[33],"this":[34],"article,":[35],"we":[36,57,162],"take":[37],"a":[38,52,111],"more":[39],"restrictive":[40],"view":[41],"toward":[42],"adversary":[43],"generation\u2014with":[44],"goal":[46],"unveiling":[48],"limits":[50],"model\u2019s":[53],"vulnerability.":[54],"In":[55,158],"particular,":[56],"explore":[58,144],"minimalistic":[59],"attacks":[60],"defining":[62],"<italic":[63,70,95,116],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[64,71,96,117],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">three":[65],"key":[66,141],"settings</i>":[67],":":[68,75,99,121],"1)":[69,166],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Black-Box":[72],"Policy":[73],"Access</i>":[74],"where":[76,100,122],"attacker":[78],"only":[79,101,123,193],"has":[80],"access":[81],"to":[82,129],"input":[84,179],"(state)":[85],"and":[86,114,143,181],"output":[87],"(action":[88],"probability)":[89],"an":[91],"RL":[92],"policy;":[93],"2)":[94,182],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Fractional-State":[97],"Adversary</i>":[98],"several":[102],"pixels":[103],"are":[104,126],"perturbed,":[105],"with":[106],"extreme":[108],"case":[109],"being":[110],"single-pixel":[112],"adversary;":[113],"3)":[115],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Tactically":[118],"Chanced":[119],"Attack</i>":[120],"significant":[124,170],"frames":[125],"tactically":[127],"chosen":[128],"attacked.":[131],"We":[132],"formulate":[133],"attack":[136],"accommodating":[138],"three":[140],"settings,":[142],"their":[145],"potency":[146],"on":[147],"six":[148],"Atari":[149],"games":[150],"examining":[152],"four":[153],"fully":[154],"trained":[155,185],"state-of-the-art":[156],"policies.":[157],"Breakout,":[159],"for":[160],"example,":[161],"surprisingly":[163],"find":[164],"that:":[165],"all":[167],"showcase":[169],"performance":[171],"degradation":[172],"merely":[174],"modifying":[175],"0.01%":[176],"state":[180],"DQN":[187],"is":[188],"totally":[189],"deceived":[190],"1%":[194],"frames.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}