{"id":"https://openalex.org/W4405785074","doi":"https://doi.org/10.1109/iros58592.2024.10802066","title":"Mitigating Adversarial Perturbations for Deep Reinforcement Learning via Vector Quantization","display_name":"Mitigating Adversarial Perturbations for Deep Reinforcement Learning via Vector Quantization","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405785074","doi":"https://doi.org/10.1109/iros58592.2024.10802066"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10802066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5028393159","display_name":"Tung M. Luu","orcid":"https://orcid.org/0000-0001-9488-7463"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Tung M. Luu","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,School of Electrical Engineering,Daejeon,Republic of Korea,34141"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,School of Electrical Engineering,Daejeon,Republic of Korea,34141","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085593383","display_name":"Thanh Thi Nguyen","orcid":"https://orcid.org/0000-0001-9709-1663"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Thanh Nguyen","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,School of Electrical Engineering,Daejeon,Republic of Korea,34141"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,School of Electrical Engineering,Daejeon,Republic of Korea,34141","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102011967","display_name":"Tee Joshua Tian Jin","orcid":"https://orcid.org/0009-0001-5119-2802"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Tee Joshua Tian Jin","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,School of Electrical Engineering,Daejeon,Republic of Korea,34141"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,School of Electrical Engineering,Daejeon,Republic of Korea,34141","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077012629","display_name":"Sungwoon Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sungwoon Kim","raw_affiliation_strings":["Korea University,Department of Artificial Intelligence,Seoul,Republic of Korea,02841"],"affiliations":[{"raw_affiliation_string":"Korea University,Department of Artificial Intelligence,Seoul,Republic of Korea,02841","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073287748","display_name":"Chang D. Yoo","orcid":"https://orcid.org/0000-0002-0756-7179"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chang D. Yoo","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,School of Electrical Engineering,Daejeon,Republic of Korea,34141"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,School of Electrical Engineering,Daejeon,Republic of Korea,34141","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5028393159"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21492025,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"595","last_page":"602"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9944000244140625,"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":0.9944000244140625,"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/adversarial-system","display_name":"Adversarial system","score":0.8773725032806396},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6355275511741638},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6051374673843384},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5097646117210388},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.5079169869422913},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48325711488723755},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21189773082733154}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8773725032806396},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6355275511741638},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6051374673843384},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5097646117210388},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.5079169869422913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48325711488723755},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21189773082733154}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10802066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":53,"referenced_works":["https://openalex.org/W1510432098","https://openalex.org/W1607267878","https://openalex.org/W2145339207","https://openalex.org/W2605102758","https://openalex.org/W2607219512","https://openalex.org/W2746553466","https://openalex.org/W2752796333","https://openalex.org/W2774018344","https://openalex.org/W2909906617","https://openalex.org/W2941205169","https://openalex.org/W2962755762","https://openalex.org/W2962933288","https://openalex.org/W2963100962","https://openalex.org/W2983498217","https://openalex.org/W3185519452","https://openalex.org/W3186158026","https://openalex.org/W4285154955","https://openalex.org/W6637162671","https://openalex.org/W6640425456","https://openalex.org/W6677408164","https://openalex.org/W6690026940","https://openalex.org/W6725195833","https://openalex.org/W6729756640","https://openalex.org/W6733049761","https://openalex.org/W6737897983","https://openalex.org/W6739868092","https://openalex.org/W6740552771","https://openalex.org/W6745272055","https://openalex.org/W6746973458","https://openalex.org/W6747027214","https://openalex.org/W6747473740","https://openalex.org/W6748204703","https://openalex.org/W6748839928","https://openalex.org/W6756840741","https://openalex.org/W6759129252","https://openalex.org/W6771740491","https://openalex.org/W6774966973","https://openalex.org/W6776438516","https://openalex.org/W6776601253","https://openalex.org/W6776867236","https://openalex.org/W6776901495","https://openalex.org/W6781541518","https://openalex.org/W6781755612","https://openalex.org/W6783055306","https://openalex.org/W6789484704","https://openalex.org/W6796183756","https://openalex.org/W6796589144","https://openalex.org/W6797106545","https://openalex.org/W6798193259","https://openalex.org/W6838240175","https://openalex.org/W6838695150","https://openalex.org/W6845898014","https://openalex.org/W6846550254"],"related_works":["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","https://openalex.org/W3209251257"],"abstract_inverted_index":{"Recent":[0],"studies":[1],"reveal":[2],"that":[3,147],"well-performing":[4],"reinforcement":[5],"learning":[6],"(RL)":[7],"agents":[8,135],"in":[9,31,109,142],"training":[10,61],"often":[11],"lack":[12],"resilience":[13],"against":[14,136,156],"adversarial":[15,104,127,137,157],"perturbations":[16],"during":[17,106],"deployment.":[18],"This":[19],"highlights":[20],"the":[21,32,50,53,62,101,110,131,151,160],"importance":[22],"of":[23,52,85,103,133],"building":[24],"a":[25,83,90],"robust":[26,41],"agent":[27,63],"before":[28],"deploying":[29],"it":[30],"real":[33],"world.":[34],"Most":[35],"prior":[36],"works":[37],"focus":[38],"on":[39,64,159],"developing":[40],"training-based":[42],"procedures":[43],"to":[44,99],"tackle":[45],"this":[46,68],"problem,":[47],"including":[48],"enhancing":[49,130],"robustness":[51,132],"deep":[54],"neural":[55],"network":[56],"component":[57],"itself":[58],"or":[59],"adversarially":[60],"strong":[65],"attacks.":[66,117,138],"In":[67],"work,":[69],"we":[70,80,145],"instead":[71],"study":[72],"an":[73],"input":[74,93,152],"transformation-based":[75],"defense":[76],"for":[77,92],"RL.":[78],"Specifically,":[79],"propose":[81],"using":[82,148],"variant":[84],"vector":[86],"quantization":[87],"(VQ)":[88],"as":[89,150],"transformation":[91,153],"observations,":[94],"which":[95],"is":[96,120],"then":[97],"used":[98],"reduce":[100],"space":[102],"attacks":[105,158],"testing,":[107],"resulting":[108],"transformed":[111],"observations":[112],"being":[113],"less":[114],"affected":[115],"by":[116],"Our":[118],"method":[119],"computationally":[121],"efficient":[122],"and":[123],"seamlessly":[124],"integrates":[125],"with":[126],"training,":[128],"further":[129],"RL":[134],"Through":[139],"extensive":[140],"experiments":[141],"multiple":[143],"environments,":[144],"demonstrate":[146],"VQ":[149],"effectively":[154],"defends":[155],"agent\u2019s":[161],"observations.":[162]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}