{"id":"https://openalex.org/W3032106256","doi":"https://doi.org/10.1145/3374135.3385288","title":"Effects of and Defenses Against Adversarial Attacks on a Traffic Light Classification CNN","display_name":"Effects of and Defenses Against Adversarial Attacks on a Traffic Light Classification CNN","publication_year":2020,"publication_date":"2020-04-02","ids":{"openalex":"https://openalex.org/W3032106256","doi":"https://doi.org/10.1145/3374135.3385288","mag":"3032106256"},"language":"en","primary_location":{"id":"doi:10.1145/3374135.3385288","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3374135.3385288","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM Southeast Conference","raw_type":"proceedings-article"},"type":"conference-paper","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/A5070169494","display_name":"Morris Wan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Morris Wan","raw_affiliation_strings":["Wheeler High School, Marietta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wheeler High School, Marietta, GA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100785901","display_name":"Meng Han","orcid":"https://orcid.org/0000-0001-7472-0842"},"institutions":[{"id":"https://openalex.org/I172980758","display_name":"Kennesaw State University","ror":"https://ror.org/00jeqjx33","country_code":"US","type":"education","lineage":["https://openalex.org/I172980758"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Meng Han","raw_affiliation_strings":["Kennesaw State University, Marietta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kennesaw State University, Marietta, GA, USA","institution_ids":["https://openalex.org/I172980758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412815","display_name":"Lin Li","orcid":"https://orcid.org/0000-0001-7553-6916"},"institutions":[{"id":"https://openalex.org/I172980758","display_name":"Kennesaw State University","ror":"https://ror.org/00jeqjx33","country_code":"US","type":"education","lineage":["https://openalex.org/I172980758"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lin Li","raw_affiliation_strings":["Kennesaw State University, Marietta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kennesaw State University, Marietta, GA, USA","institution_ids":["https://openalex.org/I172980758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100363805","display_name":"Zhigang Li","orcid":"https://orcid.org/0000-0002-6230-6959"},"institutions":[{"id":"https://openalex.org/I172980758","display_name":"Kennesaw State University","ror":"https://ror.org/00jeqjx33","country_code":"US","type":"education","lineage":["https://openalex.org/I172980758"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhigang Li","raw_affiliation_strings":["Kennesaw State University, Marietta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kennesaw State University, Marietta, GA, USA","institution_ids":["https://openalex.org/I172980758"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087326137","display_name":"Selena He","orcid":"https://orcid.org/0000-0002-2332-9816"},"institutions":[{"id":"https://openalex.org/I172980758","display_name":"Kennesaw State University","ror":"https://ror.org/00jeqjx33","country_code":"US","type":"education","lineage":["https://openalex.org/I172980758"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Selena He","raw_affiliation_strings":["Kennesaw State University, Marietta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kennesaw State University, Marietta, GA, USA","institution_ids":["https://openalex.org/I172980758"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"94","last_page":"99"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9998000264167786,"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":0.9998000264167786,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9886000156402588,"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/T14117","display_name":"Integrated Circuits and Semiconductor Failure Analysis","score":0.9546999931335449,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7962681651115417},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7631403207778931},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.727612316608429},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6809912919998169},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6118769645690918},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5380861759185791},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.5351698398590088},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.512911319732666},{"id":"https://openalex.org/keywords/resilience","display_name":"Resilience (materials science)","score":0.4747006297111511},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4240609407424927},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.41249457001686096},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3812011182308197},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3565562963485718}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7962681651115417},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7631403207778931},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.727612316608429},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6809912919998169},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6118769645690918},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5380861759185791},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5351698398590088},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.512911319732666},{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.4747006297111511},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4240609407424927},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.41249457001686096},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3812011182308197},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3565562963485718},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3374135.3385288","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3374135.3385288","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM Southeast Conference","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":11,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2070814342","https://openalex.org/W2620038827","https://openalex.org/W2765424254","https://openalex.org/W2963070423","https://openalex.org/W2963178695","https://openalex.org/W2975763460","https://openalex.org/W3103557498","https://openalex.org/W4234552385","https://openalex.org/W4299522686","https://openalex.org/W4365800068"],"related_works":["https://openalex.org/W3176659669","https://openalex.org/W2950183588","https://openalex.org/W3080754722","https://openalex.org/W4383221314","https://openalex.org/W3093978547","https://openalex.org/W2953536436","https://openalex.org/W3203790781","https://openalex.org/W4313346231","https://openalex.org/W2738001131","https://openalex.org/W4285785480"],"abstract_inverted_index":{"Convolutional":[0],"Neural":[1],"networks":[2,213],"(CNNs)":[3],"have":[4],"become":[5],"more":[6,8,174],"and":[7,16,48,52,59,69,103,138,183,228],"prevalent":[9],"in":[10,98,150,189],"applications":[11],"such":[12],"as":[13,39],"image":[14],"recognition":[15],"autonomous":[17],"driving.":[18],"However,":[19,168],"recent":[20],"literature":[21],"shows":[22,193],"that":[23,83,194,201],"a":[24,72,132,159,197],"lot":[25,198],"of":[26,135,199,210],"these":[27,124],"deep-learning":[28],"algorithms":[29,47],"are":[30],"susceptible":[31,91,175],"to":[32,35,92,118,123,176,203,206],"small":[33],"perturbations":[34],"their":[36],"input":[37],"known":[38],"adversarial":[40,45,215],"attacks.":[41,125,216,248],"In":[42,217],"this":[43,169],"project,":[44],"attack":[46,95,106,147,157,179,186],"defenses":[49],"were":[50,116,239],"implemented":[51,221,235],"evaluated":[53],"using":[54],"real":[55],"traffic":[56,222],"lights":[57],"data":[58],"model.":[60],"Using":[61],"the":[62,84,93,104,120,127,145,155,172,177,184,208,220,226,247],"spatial,":[63],"one-pixel,":[64],"Carlini":[65],"&":[66],"Wagner":[67],"(C&W),":[68],"boundary":[70],"attacks,":[71],"traffic-light":[73],"classification":[74],"neural":[75,212],"network's":[76],"robustness":[77,209],"was":[78,81,88,129,165],"evaluated.":[79],"It":[80],"found":[82],"particular":[85],"model":[86,128,173],"architecture":[87],"only":[89,170,225],"really":[90],"spatial":[94,146,185,227],"(56%":[96],"decrease":[97,149],"accuracy":[99,108],"on":[100,109,131],"perturbed":[101,110,137],"images)":[102],"C&W":[105,156,178,229],"(0%":[107],"images).":[111],"Subsequently,":[112],"two":[113,236],"defense":[114],"strategies":[115,238],"proposed":[117],"increase":[119,188,207],"model's":[121],"resilience":[122],"First,":[126],"trained":[130],"dataset":[133],"composed":[134],"both":[136],"unperturbed":[139],"images.":[140],"This":[141,192],"significantly":[142],"helped":[143],"against":[144,214,246],"(22.5%":[148],"success":[151,161,181,190],"rate).":[152,191],"Second,":[153],"since":[154],"maintained":[158],"100%":[160],"rate,":[162],"defensive":[163,237],"distillation":[164],"then":[166],"implemented.":[167],"made":[171],"(same":[180],"rate)":[182],"(13%":[187],"there":[195],"is":[196],"work":[200],"needs":[202],"be":[204],"done":[205],"applied":[211],"summary,":[218],"for":[219],"light":[223],"CNN,":[224],"attacks":[230],"can":[231],"fool":[232],"it.":[233],"The":[234],"either":[240],"marginally":[241],"successful":[242],"or":[243],"completely":[244],"failed":[245]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}