{"id":"https://openalex.org/W4312232398","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892170","title":"An Information Geometric Perspective to Adversarial Attacks and Defenses","display_name":"An Information Geometric Perspective to Adversarial Attacks and Defenses","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4312232398","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892170"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn55064.2022.9892170","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892170","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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/A5010418516","display_name":"Kyle Naddeo","orcid":null},"institutions":[{"id":"https://openalex.org/I44265643","display_name":"Rowan University","ror":"https://ror.org/049v69k10","country_code":"US","type":"education","lineage":["https://openalex.org/I44265643"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kyle Naddeo","raw_affiliation_strings":["Rowan University,Department of Electrical and Computer Engineering,Glassboro New Jersey,USA","Department of Electrical and Computer Engineering, Rowan University, Glassboro New Jersey, USA"],"affiliations":[{"raw_affiliation_string":"Rowan University,Department of Electrical and Computer Engineering,Glassboro New Jersey,USA","institution_ids":["https://openalex.org/I44265643"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Rowan University, Glassboro New Jersey, USA","institution_ids":["https://openalex.org/I44265643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041401460","display_name":"Nidhal Bouaynaya","orcid":"https://orcid.org/0000-0002-8833-8414"},"institutions":[{"id":"https://openalex.org/I44265643","display_name":"Rowan University","ror":"https://ror.org/049v69k10","country_code":"US","type":"education","lineage":["https://openalex.org/I44265643"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nidhal Bouaynaya","raw_affiliation_strings":["Rowan University,Department of Electrical and Computer Engineering,Glassboro New Jersey,USA","Department of Electrical and Computer Engineering, Rowan University, Glassboro New Jersey, USA"],"affiliations":[{"raw_affiliation_string":"Rowan University,Department of Electrical and Computer Engineering,Glassboro New Jersey,USA","institution_ids":["https://openalex.org/I44265643"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Rowan University, Glassboro New Jersey, USA","institution_ids":["https://openalex.org/I44265643"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028887750","display_name":"Roman Shterenberg","orcid":"https://orcid.org/0000-0001-7088-5711"},"institutions":[{"id":"https://openalex.org/I32389192","display_name":"University of Alabama at Birmingham","ror":"https://ror.org/008s83205","country_code":"US","type":"education","lineage":["https://openalex.org/I32389192"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roman Shterenberg","raw_affiliation_strings":["University of Alabama at Birmingham,Department of Mathematics,Birmingham Alabama,USA","Department of Mathematics, University of Alabama at Birmingham, Birmingham Alabama, USA"],"affiliations":[{"raw_affiliation_string":"University of Alabama at Birmingham,Department of Mathematics,Birmingham Alabama,USA","institution_ids":["https://openalex.org/I32389192"]},{"raw_affiliation_string":"Department of Mathematics, University of Alabama at Birmingham, Birmingham Alabama, USA","institution_ids":["https://openalex.org/I32389192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5010418516"],"corresponding_institution_ids":["https://openalex.org/I44265643"],"apc_list":null,"apc_paid":null,"fwci":0.1039,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.31388709,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"abs/1905.10615","issue":null,"first_page":"1","last_page":"8"},"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/T11515","display_name":"Bacillus and Francisella bacterial research","score":0.964900016784668,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9646000266075134,"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/mnist-database","display_name":"MNIST database","score":0.7453415393829346},{"id":"https://openalex.org/keywords/fisher-information","display_name":"Fisher information","score":0.6873976588249207},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.594648003578186},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5573900938034058},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5252601504325867},{"id":"https://openalex.org/keywords/manifold","display_name":"Manifold (fluid mechanics)","score":0.5132341384887695},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4922312796115875},{"id":"https://openalex.org/keywords/information-geometry","display_name":"Information geometry","score":0.477398544549942},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.47603562474250793},{"id":"https://openalex.org/keywords/euclidean-geometry","display_name":"Euclidean geometry","score":0.4724315106868744},{"id":"https://openalex.org/keywords/eigenvalues-and-eigenvectors","display_name":"Eigenvalues and eigenvectors","score":0.4721548557281494},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40469032526016235},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3838039040565491},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3812897503376007},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3735358715057373},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22552087903022766},{"id":"https://openalex.org/keywords/curvature","display_name":"Curvature","score":0.10402363538742065}],"concepts":[{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.7453415393829346},{"id":"https://openalex.org/C29406490","wikidata":"https://www.wikidata.org/wiki/Q1420659","display_name":"Fisher information","level":2,"score":0.6873976588249207},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.594648003578186},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5573900938034058},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5252601504325867},{"id":"https://openalex.org/C529865628","wikidata":"https://www.wikidata.org/wiki/Q1790740","display_name":"Manifold (fluid mechanics)","level":2,"score":0.5132341384887695},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4922312796115875},{"id":"https://openalex.org/C109546454","wikidata":"https://www.wikidata.org/wiki/Q3798604","display_name":"Information geometry","level":4,"score":0.477398544549942},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.47603562474250793},{"id":"https://openalex.org/C129782007","wikidata":"https://www.wikidata.org/wiki/Q162886","display_name":"Euclidean geometry","level":2,"score":0.4724315106868744},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.4721548557281494},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40469032526016235},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3838039040565491},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3812897503376007},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3735358715057373},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22552087903022766},{"id":"https://openalex.org/C195065555","wikidata":"https://www.wikidata.org/wiki/Q214881","display_name":"Curvature","level":2,"score":0.10402363538742065},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C12520029","wikidata":"https://www.wikidata.org/wiki/Q1147161","display_name":"Scalar curvature","level":3,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn55064.2022.9892170","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892170","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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":0.41999998688697815}],"awards":[{"id":"https://openalex.org/G2141436875","display_name":null,"funder_award_id":"EP/T013265/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1945616565","https://openalex.org/W2007339694","https://openalex.org/W2112796928","https://openalex.org/W2137983211","https://openalex.org/W2597490979","https://openalex.org/W2618098489","https://openalex.org/W2948210185","https://openalex.org/W2963163009","https://openalex.org/W2963671728","https://openalex.org/W2963969878","https://openalex.org/W2972672017","https://openalex.org/W2993903663","https://openalex.org/W2996343955","https://openalex.org/W3118608800","https://openalex.org/W4229633200","https://openalex.org/W4288335177","https://openalex.org/W4293363567","https://openalex.org/W4297775537","https://openalex.org/W6637162671","https://openalex.org/W6640425456","https://openalex.org/W6735419579","https://openalex.org/W6738856548","https://openalex.org/W6755437632","https://openalex.org/W6762427411","https://openalex.org/W6763735624","https://openalex.org/W6767503882","https://openalex.org/W6786886800"],"related_works":["https://openalex.org/W1997179310","https://openalex.org/W1964020044","https://openalex.org/W2123013354","https://openalex.org/W3100234836","https://openalex.org/W2125882322","https://openalex.org/W1899173975","https://openalex.org/W1969904786","https://openalex.org/W2914965186","https://openalex.org/W1609560631","https://openalex.org/W2034813183"],"abstract_inverted_index":{"Deep":[0],"learning":[1,55],"models":[2,31],"have":[3],"achieved":[4],"state-of-the-art":[5],"accuracy":[6],"in":[7],"complex":[8],"tasks,":[9],"sometimes":[10],"outperforming":[11],"human-level":[12],"accuracy.":[13],"Yet,":[14],"they":[15],"suffer":[16],"from":[17],"vulnerabilities":[18],"known":[19],"as":[20,85,93,107],"adversarial":[21,40,64],"attacks,":[22],"which":[23],"are":[24],"imperceptible":[25],"input":[26,81],"perturbations":[27],"that":[28,34,59,128],"fool":[29],"the":[30,63,72,77,80,90,102,108,112,116,122,133,141,146,153,157,162,166,172,177],"on":[32,184],"inputs":[33],"were":[35],"originally":[36],"classified":[37],"correctly.":[38],"The":[39],"problem":[41],"remains":[42],"poorly":[43],"understood":[44],"and":[45,61,75,82,176,189,196],"commonly":[46],"thought":[47],"to":[48,69,111],"be":[49],"an":[50,129],"inherent":[51],"weakness":[52],"of":[53,115,132,149,165],"deep":[54],"models.":[56],"We":[57,126,160],"argue":[58],"understanding":[60],"alleviating":[62],"phenomenon":[65],"may":[66],"require":[67],"us":[68],"go":[70],"beyond":[71],"Euclidean":[73],"view":[74],"consider":[76],"relationship":[78],"between":[79],"output":[83],"spaces":[84],"a":[86],"statistical":[87],"manifold":[88,138],"with":[89],"Fisher":[91,117,123,173],"Information":[92,118],"its":[94,137],"Riemannian":[95],"metric.":[96],"Under":[97],"this":[98],"information":[99],"geometric":[100],"view,":[101],"optimal":[103,147],"attack":[104,175],"is":[105],"constructed":[106],"direction":[109,148],"corresponding":[110],"highest":[113,142],"eigenvalue":[114,143],"Matrix":[119],"-":[120,170,183],"called":[121],"spectral":[124,174],"attack.":[125],"show":[127],"orthogonal":[130,168],"transformation":[131],"data":[134,193],"cleverly":[135],"alters":[136],"by":[139],"keeping":[140],"but":[144],"changing":[145],"attack;":[150],"thus":[151],"deceiving":[152],"attacker":[154],"into":[155],"adopting":[156],"wrong":[158],"direction.":[159],"demonstrate":[161],"defensive":[163],"capabilities":[164],"proposed":[167],"scheme":[169],"against":[171],"popular":[178],"fast":[179],"gradient":[180],"sign":[181],"method":[182],"standard":[185],"networks,":[186],"e.g.,":[187],"LeNet":[188],"MobileNetV2":[190],"for":[191],"benchmark":[192],"sets,":[194],"MNIST":[195],"CIFAR-10.":[197]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}