{"id":"https://openalex.org/W2963268689","doi":"https://doi.org/10.1145/3219819.3219910","title":"SHIELD","display_name":"SHIELD","publication_year":2018,"publication_date":"2018-07-19","ids":{"openalex":"https://openalex.org/W2963268689","doi":"https://doi.org/10.1145/3219819.3219910","mag":"2963268689"},"language":"en","primary_location":{"id":"doi:10.1145/3219819.3219910","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3219819.3219910","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3219819.3219910","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3219819.3219910","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036502813","display_name":"Nilaksh Das","orcid":"https://orcid.org/0000-0002-5281-5549"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nilaksh Das","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021062067","display_name":"Madhuri Shanbhogue","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Madhuri Shanbhogue","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079496618","display_name":"Shang-Tse Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shang-Tse Chen","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034842879","display_name":"Fred Hohman","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fred Hohman","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100733089","display_name":"Siwei Li","orcid":"https://orcid.org/0000-0003-1538-1937"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siwei Li","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100379250","display_name":"Li Chen","orcid":"https://orcid.org/0000-0002-4761-5913"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Chen","raw_affiliation_strings":["Intel Corporation, Hillsboro, OR, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation, Hillsboro, OR, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063555801","display_name":"Michael E. Kounavis","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael E. Kounavis","raw_affiliation_strings":["Intel Corporation, Hillsboro, OR, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation, Hillsboro, OR, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020153026","display_name":"Duen Horng Chau","orcid":"https://orcid.org/0000-0001-9824-3323"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Duen Horng Chau","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":16.0508,"has_fulltext":false,"cited_by_count":162,"citation_normalized_percentile":{"value":0.99160128,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"196","last_page":"204"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9830999970436096,"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":0.9739000201225281,"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/computer-science","display_name":"Computer science","score":0.8238510489463806},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5961241126060486},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5187630653381348},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.4981803894042969},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4910728931427002},{"id":"https://openalex.org/keywords/shield","display_name":"Shield","score":0.4618465304374695},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.45827531814575195},{"id":"https://openalex.org/keywords/adversary","display_name":"Adversary","score":0.4428390860557556},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4389049708843231},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42886608839035034},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3829079866409302},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.22056177258491516}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8238510489463806},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5961241126060486},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5187630653381348},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.4981803894042969},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4910728931427002},{"id":"https://openalex.org/C138081364","wikidata":"https://www.wikidata.org/wiki/Q852013","display_name":"Shield","level":2,"score":0.4618465304374695},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.45827531814575195},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.4428390860557556},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4389049708843231},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42886608839035034},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3829079866409302},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.22056177258491516},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C5900021","wikidata":"https://www.wikidata.org/wiki/Q163082","display_name":"Petrology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3219819.3219910","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3219819.3219910","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3219819.3219910","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3219819.3219910","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3219819.3219910","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3219819.3219910","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being"}],"awards":[{"id":"https://openalex.org/G7182034009","display_name":null,"funder_award_id":"1704701","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1883420340","https://openalex.org/W2166128942","https://openalex.org/W2180612164","https://openalex.org/W2217248474","https://openalex.org/W2243397390","https://openalex.org/W2503523779","https://openalex.org/W2535873859","https://openalex.org/W2543927648","https://openalex.org/W2593892853","https://openalex.org/W2603766943","https://openalex.org/W2607219512","https://openalex.org/W2618530766","https://openalex.org/W2741933435","https://openalex.org/W2765384636","https://openalex.org/W2772699819","https://openalex.org/W2778115935","https://openalex.org/W2787708942","https://openalex.org/W2904025731","https://openalex.org/W2941205169","https://openalex.org/W2963207607","https://openalex.org/W2963834268","https://openalex.org/W2963857521","https://openalex.org/W2964082701","https://openalex.org/W2964153729"],"related_works":["https://openalex.org/W4320018150","https://openalex.org/W2918664383","https://openalex.org/W3176659669","https://openalex.org/W203812490","https://openalex.org/W4320855730","https://openalex.org/W3123119822","https://openalex.org/W106056076","https://openalex.org/W2135200719","https://openalex.org/W2950183588","https://openalex.org/W3080754722"],"abstract_inverted_index":{"The":[0],"rapidly":[1],"growing":[2],"body":[3],"of":[4,66,124,131,143,164,193],"research":[5],"in":[6,41,53,118],"adversarial":[7,199],"machine":[8],"learning":[9],"has":[10],"demonstrated":[11],"that":[12,33,44,55,113,139,186],"deep":[13],"neural":[14],"networks":[15],"(DNNs)":[16],"are":[17,56,106,114,210],"highly":[18],"vulnerable":[19],"to":[20,38,49,75,108,156,191],"adversarially":[21],"generated":[22],"images.":[23],"This":[24,161],"underscores":[25],"the":[26,64,94,158,181,218],"urgent":[27],"need":[28],"for":[29,153],"practical":[30],"defense":[31,70],"techniques":[32,200],"can":[34],"be":[35],"readily":[36],"deployed":[37],"combat":[39],"attacks":[40,195],"real-time.":[42],"Observing":[43],"many":[45],"attack":[46,205],"strategies":[47],"aim":[48],"perturb":[50],"image":[51,145],"pixels":[52],"ways":[54],"visually":[57],"imperceptible,":[58],"we":[59],"place":[60],"JPEG":[61],"compression":[62,104,148],"at":[63,136],"core":[65],"our":[67,187],"proposed":[68],"SHIELD":[69,92,126,170],"framework,":[71],"utilizing":[72],"its":[73],"capability":[74],"effectively":[76],"\"compress":[77],"away\"":[78],"such":[79,201],"pixel":[80],"manipulation.":[81],"To":[82],"immunize":[83],"a":[84,171],"DNN":[85],"model":[86,95],"from":[87],"artifacts":[88],"introduced":[89],"by":[90,96,133,197],"compression,":[91],"\"vaccinates\"":[93],"retraining":[97],"it":[98,151],"with":[99],"compressed":[100],"images,":[101],"where":[102],"different":[103,141],"levels":[105],"applied":[107],"generate":[109],"multiple":[110],"vaccinated":[111],"models":[112],"ultimately":[115],"used":[116],"together":[117],"an":[119,128,144,154],"ensemble":[120],"defense.":[121,174],"On":[122],"top":[123],"that,":[125],"adds":[127],"additional":[129],"layer":[130],"protection":[132],"employing":[134],"randomization":[135,168],"test":[137],"time":[138],"compresses":[140],"regions":[142],"using":[146,180],"random":[147],"levels,":[149],"making":[150],"harder":[152],"adversary":[155],"estimate":[157],"transformation":[159],"performed.":[160],"novel":[162],"combination":[163],"vaccination,":[165],"ensembling,":[166],"and":[167,184,206,212],"makes":[169],"fortified":[172],"multi-pronged":[173],"We":[175],"conducted":[176],"extensive,":[177],"large-scale":[178],"experiments":[179],"ImageNet":[182],"dataset,":[183],"show":[185],"approaches":[188,209],"eliminate":[189],"up":[190],"98%":[192],"gray-box":[194],"delivered":[196],"strong":[198],"as":[202],"Carlini-Wagner's":[203],"L2":[204],"DeepFool.":[207],"Our":[208],"fast":[211],"work":[213],"without":[214],"requiring":[215],"knowledge":[216],"about":[217],"model.":[219]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":20},{"year":2021,"cited_by_count":38},{"year":2020,"cited_by_count":33},{"year":2019,"cited_by_count":21},{"year":2018,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2019-07-30T00:00:00"}