{"id":"https://openalex.org/W4414604597","doi":"https://doi.org/10.1109/qrs65678.2025.00026","title":"Diagnosing Deep Learning Errors with Reinforcement Learning-Driven Adversarial Examples","display_name":"Diagnosing Deep Learning Errors with Reinforcement Learning-Driven Adversarial Examples","publication_year":2025,"publication_date":"2025-07-16","ids":{"openalex":"https://openalex.org/W4414604597","doi":"https://doi.org/10.1109/qrs65678.2025.00026"},"language":"en","primary_location":{"id":"doi:10.1109/qrs65678.2025.00026","is_oa":false,"landing_page_url":"https://doi.org/10.1109/qrs65678.2025.00026","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 25th International Conference on Software Quality, Reliability and Security (QRS)","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/A5032344956","display_name":"Kaicheng Shao","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaicheng Shao","raw_affiliation_strings":["Peking University,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023121498","display_name":"Yuteng Lu","orcid":"https://orcid.org/0000-0001-6315-7767"},"institutions":[{"id":"https://openalex.org/I4210129465","display_name":"Wuhan Ship Development & Design Institute","ror":"https://ror.org/02mcdae06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210129465"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuteng Lu","raw_affiliation_strings":["China Ship Research and Development Academy,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Ship Research and Development Academy,Beijing,China","institution_ids":["https://openalex.org/I4210129465"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021905916","display_name":"Liu Ai","orcid":"https://orcid.org/0000-0001-8222-2157"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ai Liu","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics,Nanjing,China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024021805","display_name":"Meng Sun","orcid":"https://orcid.org/0000-0001-6550-7396"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Sun","raw_affiliation_strings":["Peking University,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12422728,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"154","last_page":"163"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9847999811172485,"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":0.9847999811172485,"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":0.8023999929428101},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7060999870300293},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.6869000196456909},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6603999733924866},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6146000027656555},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.48489999771118164},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4726000130176544},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.44769999384880066}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8023999929428101},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7479000091552734},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7271999716758728},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7060999870300293},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.6869000196456909},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6780999898910522},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6603999733924866},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6146000027656555},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.48489999771118164},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4726000130176544},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.44769999384880066},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4219000041484833},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4142000079154968},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.39989998936653137},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.39149999618530273},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2777000069618225},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.25859999656677246},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2538999915122986},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.25380000472068787},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/qrs65678.2025.00026","is_oa":false,"landing_page_url":"https://doi.org/10.1109/qrs65678.2025.00026","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 25th International Conference on Software Quality, Reliability and Security (QRS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2010007046","display_name":null,"funder_award_id":"62172019","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W3160369295","https://openalex.org/W4382317555","https://openalex.org/W4382457976","https://openalex.org/W4384155620","https://openalex.org/W4384302763","https://openalex.org/W4384302789","https://openalex.org/W4384304645","https://openalex.org/W4384345694","https://openalex.org/W4387211660","https://openalex.org/W4391579639","https://openalex.org/W4391579668","https://openalex.org/W4393159541","https://openalex.org/W4393159796","https://openalex.org/W4394625665","https://openalex.org/W4394769550"],"related_works":[],"abstract_inverted_index":{"Adversarial":[0],"examples":[1],"have":[2],"become":[3],"a":[4,64],"critical":[5],"focus":[6],"in":[7,37,102,120,146],"ensuring":[8],"the":[9,84,113,122,130],"security":[10],"and":[11,33,50,60,78,86,89],"robustness":[12],"of":[13,108,116,124,132],"deep":[14],"learning":[15,66],"(DL)":[16],"systems.":[17],"In":[18],"this":[19],"paper,":[20],"we":[21,68,128],"introduce":[22],"an":[23],"innovative":[24],"approach":[25,92],"for":[26],"generating":[27],"adversarial":[28],"examples,":[29],"designed":[30],"to":[31,141],"identify":[32],"diagnose":[34,142],"common":[35,144],"errors":[36,145],"DL":[38,125,147],"models.":[39,109,126],"Specifically,":[40],"our":[41,91,117,133],"method":[42,119],"targets":[43],"two":[44],"key":[45],"issues:":[46],"Oscillating":[47],"Loss":[48],"(OL)":[49],"Slow":[51],"Convergence":[52],"(SC),":[53],"providing":[54],"valuable":[55],"insight":[56],"into":[57],"model":[58],"performance":[59],"fault":[61],"detection.":[62],"Using":[63],"reinforcement":[65],"framework,":[67],"generate":[69],"test":[70,90],"data":[71],"that":[72,136],"effectively":[73],"distinguishes":[74],"between":[75],"models":[76,148],"with":[77,96,149],"without":[79],"these":[80],"errors.":[81],"We":[82],"consider":[83],"MNIST":[85],"CIFAR-10":[87],"datasets":[88],"on":[93],"neural":[94],"networks":[95],"various":[97,143],"architectures,":[98],"demonstrating":[99],"significant":[100],"improvements":[101],"error":[103],"detection":[104],"across":[105],"different":[106],"types":[107],"These":[110],"results":[111],"highlight":[112],"substantial":[114],"effectiveness":[115],"proposed":[118],"improving":[121],"reliability":[123],"Furthermore,":[127],"demonstrate":[129],"scalability":[131],"approach,":[134],"showing":[135],"it":[137],"can":[138],"be":[139],"used":[140],"minimal":[150],"modifications.":[151]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}