{"id":"https://openalex.org/W2995823288","doi":null,"title":"Adversarially Robust Representations with Smooth Encoders","display_name":"Adversarially Robust Representations with Smooth Encoders","publication_year":2020,"publication_date":"2020-04-30","ids":{"openalex":"https://openalex.org/W2995823288","mag":"2995823288"},"language":"en","primary_location":{"id":"mag:2995823288","doi":null,"is_oa":false,"landing_page_url":"https://openreview.net/pdf?id=H1gfFaEYDS","pdf_url":null,"source":{"id":"https://openalex.org/S4306419637","display_name":"International Conference on Learning Representations","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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,"raw_source_name":"International Conference on Learning Representations","raw_type":null},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"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/A5064633247","display_name":"Ali Taylan Cemgil","orcid":"https://orcid.org/0000-0003-4463-8455","observed_orcids":["https://orcid.org/0000-0003-4463-8455"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali Taylan Cemgil","raw_affiliation_strings":["Google (United States), Mountain View, United States"],"raw_orcid":"https://orcid.org/0000-0003-4463-8455","affiliations":[{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070493275","display_name":"Sumedh Ghaisas","orcid":"https://orcid.org/0000-0003-3753-9029","observed_orcids":["https://orcid.org/0000-0003-3753-9029"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sumedh Ghaisas","raw_affiliation_strings":["Google (United States), Mountain View, United States"],"raw_orcid":"https://orcid.org/0000-0003-3753-9029","affiliations":[{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050954769","display_name":"Krishnamurthy Dvijotham","orcid":"https://orcid.org/0000-0002-1328-4677","observed_orcids":["https://orcid.org/0000-0002-1328-4677"]},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krishnamurthy Dvijotham","raw_affiliation_strings":["California Institute of Technology, Pasadena, United States"],"raw_orcid":"https://orcid.org/0000-0002-1328-4677","affiliations":[{"raw_affiliation_string":"California Institute of Technology, Pasadena, United States","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013834379","display_name":"Pushmeet Kohli","orcid":"https://orcid.org/0000-0002-7466-7997","observed_orcids":["https://orcid.org/0000-0002-7466-7997"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pushmeet Kohli","raw_affiliation_strings":["Google (United States), Mountain View, United States"],"raw_orcid":"https://orcid.org/0000-0002-7466-7997","affiliations":[{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0397,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.80462788,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9980000257492065,"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":0.9980000257492065,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0003000000142492354,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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-robustness","display_name":"adversarial robustness","score":0.890999972820282},{"id":"https://openalex.org/keywords/representation-learning","display_name":"representation learning","score":0.7490000128746033},{"id":"https://openalex.org/keywords/variational-autoencoder","display_name":"variational autoencoder","score":0.8849999904632568},{"id":"https://openalex.org/keywords/evidence-lower-bound","display_name":"evidence lower bound","score":0.9810000061988831},{"id":"https://openalex.org/keywords/data-augmentation","display_name":"data augmentation","score":0.5360000133514404},{"id":"https://openalex.org/keywords/entropy-regularization","display_name":"entropy regularization","score":0.6340000033378601},{"id":"https://openalex.org/keywords/wasserstein-distance","display_name":"Wasserstein distance","score":0.9869999885559082},{"id":"https://openalex.org/keywords/data-efficient-learning","display_name":"data-efficient learning","score":0.5109999775886536},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.7710000276565552}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7480078339576721},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6221692562103271},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6050258278846741},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5519923567771912},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5205591320991516},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5194013118743896},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4783739149570465},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.466705322265625},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4575677216053009},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.4488697648048401},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2995823288","doi":null,"is_oa":false,"landing_page_url":"https://openreview.net/pdf?id=H1gfFaEYDS","pdf_url":null,"source":{"id":"https://openalex.org/S4306419637","display_name":"International Conference on Learning Representations","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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,"raw_source_name":"International Conference on Learning Representations","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1511358834","https://openalex.org/W1613249581","https://openalex.org/W1909320841","https://openalex.org/W1959608418","https://openalex.org/W2129999749","https://openalex.org/W2147880316","https://openalex.org/W2163605009","https://openalex.org/W2411541852","https://openalex.org/W2412320034","https://openalex.org/W2516574342","https://openalex.org/W2552767274","https://openalex.org/W2579277680","https://openalex.org/W2594717275","https://openalex.org/W2620025707","https://openalex.org/W2753738274","https://openalex.org/W2785169672","https://openalex.org/W2795671189","https://openalex.org/W2807692250","https://openalex.org/W2902227449","https://openalex.org/W2945791915","https://openalex.org/W2953338786","https://openalex.org/W2962983186","https://openalex.org/W2963027080","https://openalex.org/W2963341956","https://openalex.org/W2964153729","https://openalex.org/W2964253222","https://openalex.org/W3148140980"],"related_works":["https://openalex.org/W2976501124","https://openalex.org/W2946956149","https://openalex.org/W3008555961","https://openalex.org/W2804853846","https://openalex.org/W3005226846","https://openalex.org/W4225526255","https://openalex.org/W7116071459","https://openalex.org/W3133199143","https://openalex.org/W3167434447","https://openalex.org/W3207676007"],"abstract_inverted_index":{"This":[0,75],"paper":[1],"studies":[2],"the":[3,27,33,41,46,49,53,56,64,72,81,99,107,155,158,179],"undesired":[4],"phenomena":[5],"of":[6,8,48,52,55,63,84,106,113,148,157],"over-sensitivity":[7],"representations":[9,85,189],"learned":[10,73],"by":[11,137,186],"deep":[12],"networks":[13],"to":[14,44,68,97,111,154,198],"semantically-irrelevant":[15],"changes":[16],"in":[17,26,71,80,178,191],"data.":[18],"We":[19,38,165],"identify":[20],"a":[21,77,121,128,133,196,199,205],"cause":[22],"for":[23,86],"this":[24,61,93],"shortcoming":[25],"classical":[28],"Variational":[29],"Auto-encoder":[30],"(VAE)":[31],"objective,":[32],"evidence":[34],"lower":[35],"bound":[36],"(ELBO).":[37],"show":[39,174],"that":[40,103,124,131,175],"ELBO":[42],"fails":[43],"control":[45],"behaviour":[47,62],"encoder":[50],"out":[51],"support":[54],"empirical":[57],"data":[58,100,135,143],"distribution":[59],"and":[60,89,172,203],"VAE":[65],"can":[66,183],"lead":[67],"extreme":[69],"errors":[70],"representation.":[74],"is":[76,125],"key":[78],"hurdle":[79],"effective":[82],"use":[83],"data-efficient":[87],"learning":[88,187],"transfer.":[90],"To":[91,115],"address":[92],"problem,":[94],"we":[95,119],"propose":[96,120],"augment":[98],"with":[101,109],"specifications":[102],"enforce":[104],"insensitivity":[105],"representation":[108],"respect":[110],"families":[112],"transformations.":[114],"incorporate":[116],"these":[117],"specifications,":[118],"regularization":[122],"method":[123],"based":[126],"on":[127,169],"selection":[129],"mechanism":[130],"creates":[132],"fictive":[134],"point":[136],"explicitly":[138],"perturbing":[139],"an":[140,192],"observed":[141],"true":[142],"point.":[144],"For":[145],"certain":[146],"choices":[147],"parameters,":[149],"our":[150,167],"formulation":[151],"naturally":[152],"leads":[153],"minimization":[156],"entropy":[159],"regularized":[160],"Wasserstein":[161],"distance":[162],"between":[163],"representations.":[164],"illustrate":[166],"approach":[168],"standard":[170],"datasets":[171],"experimentally":[173],"significant":[176],"improvements":[177],"downstream":[180,201],"adversarial":[181,208],"accuracy":[182],"be":[184],"achieved":[185],"robust":[188],"completely":[190],"unsupervised":[193],"manner,":[194],"without":[195,204],"reference":[197],"particular":[200],"task":[202],"costly":[206],"supervised":[207],"training":[209],"procedure.":[210]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2019-12-26T00:00:00"}