{"id":"https://openalex.org/W4206066549","doi":"https://doi.org/10.1109/milcom52596.2021.9653101","title":"Beyond $L_{p}$ Norms: Delving Deeper into Robustness to Physical Image Transformations","display_name":"Beyond $L_{p}$ Norms: Delving Deeper into Robustness to Physical Image Transformations","publication_year":2021,"publication_date":"2021-11-29","ids":{"openalex":"https://openalex.org/W4206066549","doi":"https://doi.org/10.1109/milcom52596.2021.9653101"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/milcom52596.2021.9653101","pdf_url":null,"source":{"id":"https://openalex.org/S4363608114","display_name":"MILCOM 2022 - 2022 IEEE Military Communications Conference (MILCOM)","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":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5011437254","display_name":"Vikash Sehwag","orcid":null},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vikash Sehwag","raw_affiliation_strings":["Princeton University, Princeton, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059859993","display_name":"Jack W. Stokes","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jack W. Stokes","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103551927","display_name":"Cha Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cha Zhang","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":57},"biblio":{"volume":null,"issue":null,"first_page":"189","last_page":"196"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.999,"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":0.999,"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":0.9879,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9631,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness","score":0.9090095}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.9090095},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6859581},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.57055265},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.47314537},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.44781965},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43861517},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42738366},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34742683},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34702784},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.17677942},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/milcom52596.2021.9653101","pdf_url":null,"source":{"id":"https://openalex.org/S4363608114","display_name":"MILCOM 2022 - 2022 IEEE Military Communications Conference (MILCOM)","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":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":28,"referenced_works":["https://openalex.org/W1945616565","https://openalex.org/W2108598243","https://openalex.org/W2119112357","https://openalex.org/W2194775991","https://openalex.org/W2325939864","https://openalex.org/W2342840547","https://openalex.org/W2557738935","https://openalex.org/W2768718880","https://openalex.org/W2905810301","https://openalex.org/W2910603373","https://openalex.org/W2945033152","https://openalex.org/W2947028053","https://openalex.org/W2952911150","https://openalex.org/W2954744211","https://openalex.org/W2963366334","https://openalex.org/W2964077693","https://openalex.org/W2964116600","https://openalex.org/W2970456043","https://openalex.org/W2981030070","https://openalex.org/W2996904338","https://openalex.org/W3008556381","https://openalex.org/W3011711787","https://openalex.org/W3027471792","https://openalex.org/W3125713917","https://openalex.org/W4288363831","https://openalex.org/W4288404646","https://openalex.org/W4293846201","https://openalex.org/W4300658615"],"related_works":["https://openalex.org/W4320855730","https://openalex.org/W4320018150","https://openalex.org/W4246396837","https://openalex.org/W3176240006","https://openalex.org/W2918664383","https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W2135200719","https://openalex.org/W2040808657","https://openalex.org/W106056076"],"abstract_inverted_index":{"With":[0],"the":[1,30,79,112,162,174],"increasing":[2],"adoption":[3],"of":[4,32,81,114,119],"deep":[5,82],"learning":[6],"in":[7,29],"computer":[8],"vision-based":[9],"applications,":[10],"it":[11],"becomes":[12],"critical":[13],"to":[14,17,116,129,171],"achieve":[15,87],"robustness":[16,60,88,105,115,122,144],"real-world":[18],"image":[19,47],"transformations,":[20,44],"such":[21,45],"as":[22,46],"geometric,":[23],"photometric,":[24],"and":[25,58],"weather":[26],"changes,":[27],"even":[28],"presence":[31],"an":[33,139],"adversary.":[34],"However,":[35],"earlier":[36],"work":[37],"has":[38],"focused":[39],"on":[40,73,93,173],"only":[41],"a":[42,153],"few":[43],"translation,":[48],"rotation,":[49],"or":[50],"coloring.":[51],"We":[52,109],"close":[53],"this":[54],"gap":[55],"by":[56,152],"analyzing":[57],"improving":[59],"against":[61,89,106,124,145,165],"twenty-four":[62,166],"different":[63,167],"physical":[64,75],"transformations.":[65],"First,":[66],"we":[67,86,97,135],"demonstrate":[68,111],"that":[69,99,137],"adversarial":[70,94],"attacks":[71,91,147],"based":[72,92],"each":[74],"transformation":[76],"significantly":[77,103],"reduce":[78],"accuracy":[80],"neural":[83],"networks.":[84],"Next,":[85],"these":[90,107,117],"training,":[95],"where":[96,121],"show":[98,136],"single-step":[100],"data":[101],"augmentation":[102],"improves":[104,161],"attacks.":[108],"also":[110,127],"generalization":[113],"types":[118],"attacks,":[120,168],"achieved":[123,150],"one":[125],"attack":[126,132],"generalizes":[128],"some":[130],"other":[131],"vectors.":[133],"Finally,":[134],"using":[138],"ensemble-based":[140],"robust":[141],"training":[142],"approach,":[143],"multiple":[146],"can":[148],"be":[149],"simultaneously":[151],"single":[154],"network.":[155],"In":[156],"particular,":[157],"our":[158],"proposed":[159],"method":[160],"aggregate":[163],"robustness,":[164],"from":[169],"21.4%":[170],"50.0%":[172],"ImageNet":[175],"dataset.":[176]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4206066549","counts_by_year":[],"updated_date":"2024-12-11T23:47:34.250285","created_date":"2022-01-26"}