{"id":"https://openalex.org/W4387968250","doi":"https://doi.org/10.1145/3581783.3612304","title":"Reinforcement Learning-based Adversarial Attacks on Object Detectors using Reward Shaping","display_name":"Reinforcement Learning-based Adversarial Attacks on Object Detectors using Reward Shaping","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968250","doi":"https://doi.org/10.1145/3581783.3612304"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612304","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612304","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st 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/A5078030239","display_name":"Zhenbo Shi","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":true,"raw_author_name":"Zhenbo Shi","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057246165","display_name":"Wei Yang","orcid":"https://orcid.org/0000-0003-0332-2649"},"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":"Wei Yang","raw_affiliation_strings":["Hefei National Laboratory & University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Hefei National Laboratory & University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021459992","display_name":"Zhenbo Xu","orcid":"https://orcid.org/0000-0002-8948-1589"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenbo Xu","raw_affiliation_strings":["Hangzhou Innovation Institute & Beihang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Hangzhou Innovation Institute & Beihang University, Hangzhou, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113536741","display_name":"Zhidong Yu","orcid":"https://orcid.org/0000-0001-7168-6423"},"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":"Zhidong Yu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019604942","display_name":"Liusheng Huang","orcid":"https://orcid.org/0000-0001-8417-3256"},"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":"Liusheng Huang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5078030239"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.533,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72718579,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"8424","last_page":"8432"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9995999932289124,"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":0.9995999932289124,"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":0.8686219453811646},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7839289903640747},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6679521203041077},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.598007082939148},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5723663568496704},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5560914278030396},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.519138753414154},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5073301196098328},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5004737377166748},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.482353150844574},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4781516492366791},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.47483307123184204},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45903778076171875},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.45251229405403137},{"id":"https://openalex.org/keywords/markov-random-field","display_name":"Markov random field","score":0.42784351110458374},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.32430750131607056},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.19380605220794678},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.10325539112091064},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08444830775260925}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8686219453811646},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7839289903640747},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6679521203041077},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.598007082939148},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5723663568496704},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5560914278030396},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.519138753414154},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5073301196098328},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5004737377166748},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.482353150844574},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4781516492366791},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.47483307123184204},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45903778076171875},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.45251229405403137},{"id":"https://openalex.org/C2778045648","wikidata":"https://www.wikidata.org/wiki/Q176827","display_name":"Markov random field","level":4,"score":0.42784351110458374},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.32430750131607056},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.19380605220794678},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.10325539112091064},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08444830775260925},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612304","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612304","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7599999904632568}],"awards":[{"id":"https://openalex.org/G5314011804","display_name":null,"funder_award_id":"2021M700346","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G5617267882","display_name":null,"funder_award_id":"62172385, 62206012","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2557728737","https://openalex.org/W2565639579","https://openalex.org/W2776055286","https://openalex.org/W2899607431","https://openalex.org/W2963149332","https://openalex.org/W2963150697","https://openalex.org/W2963351448","https://openalex.org/W2982770724","https://openalex.org/W3015443841","https://openalex.org/W3017485054","https://openalex.org/W3035262841","https://openalex.org/W3035296770","https://openalex.org/W3035524670","https://openalex.org/W3048927482","https://openalex.org/W3120052154","https://openalex.org/W3175613352","https://openalex.org/W3190929856","https://openalex.org/W4289038676"],"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/W187740018","https://openalex.org/W2162286586","https://openalex.org/W4255368532"],"abstract_inverted_index":{"In":[0,128],"the":[1,50,63,80,100],"field":[2],"of":[3,52,65],"object":[4,53,126],"detector":[5],"attacks,":[6],"previous":[7],"methods":[8],"primarily":[9],"rely":[10],"on":[11],"fixed":[12],"gradient":[13],"optimization":[14,91],"or":[15],"patch-based":[16],"cover":[17],"techniques,":[18],"often":[19],"leading":[20],"to":[21,48,110],"suboptimal":[22],"attack":[23,36],"performance":[24],"and":[25,55,88,95,108,135],"excessive":[26],"distortions.":[27],"To":[28],"address":[29],"these":[30],"limitations,":[31],"we":[32,61],"propose":[33],"a":[34,73,89,132],"novel":[35],"method,":[37],"Interactive":[38],"Reinforcement-based":[39],"Sparse":[40],"Attack":[41],"(IRSA),":[42],"which":[43],"employs":[44],"Reinforcement":[45],"Learning":[46],"(RL)":[47],"discover":[49],"vulnerabilities":[51],"detectors":[54],"systematically":[56],"generate":[57],"erroneous":[58],"results.":[59],"Specifically,":[60],"formulate":[62],"process":[64],"seeking":[66],"optimal":[67],"margins":[68],"for":[69,93],"adversarial":[70],"examples":[71],"as":[72],"Markov":[74],"Decision":[75],"Process":[76],"(MDP).":[77],"We":[78],"tackle":[79],"RL":[81],"convergence":[82],"difficulty":[83],"through":[84],"innovative":[85],"reward":[86],"functions":[87],"composite":[90],"method":[92,118],"effective":[94],"efficient":[96],"policy":[97],"training.":[98],"Moreover,":[99],"perturbations":[101],"generated":[102],"by":[103],"IRSA":[104,130],"are":[105],"more":[106],"subtle":[107],"difficult":[109],"detect":[111],"while":[112],"requiring":[113],"less":[114],"computational":[115],"effort.":[116],"Our":[117],"also":[119],"demonstrates":[120],"strong":[121],"generalization":[122],"capabilities":[123],"against":[124],"various":[125],"detectors.":[127],"summary,":[129],"is":[131],"refined,":[133],"efficient,":[134],"scalable":[136],"interactive,":[137],"iterative,":[138],"end-to-end":[139],"algorithm.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}