{"id":"https://openalex.org/W4319653905","doi":"https://doi.org/10.48550/arxiv.2302.03523","title":"Sparse Mixture Once-for-all Adversarial Training for Efficient In-Situ Trade-Off Between Accuracy and Robustness of DNNs","display_name":"Sparse Mixture Once-for-all Adversarial Training for Efficient In-Situ Trade-Off Between Accuracy and Robustness of DNNs","publication_year":2022,"publication_date":"2022-12-27","ids":{"openalex":"https://openalex.org/W4319653905","doi":"https://doi.org/10.48550/arxiv.2302.03523"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2302.03523","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2302.03523","pdf_url":"https://arxiv.org/pdf/2302.03523","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2302.03523","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087095284","display_name":"Souvik Kundu","orcid":"https://orcid.org/0000-0001-5815-8765"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Kundu, Souvik","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013199442","display_name":"Sairam Sundaresan","orcid":"https://orcid.org/0000-0002-6648-0591"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sundaresan, Sairam","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101153316","display_name":"Sharath Nittur Sridhar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sridhar, Sharath Nittur","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028455158","display_name":"Shunlin Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Shunlin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101193310","display_name":"Han Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Han","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5084205024","display_name":"Peter A. Beerel","orcid":"https://orcid.org/0000-0002-8283-0168"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Beerel, Peter A.","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5087095284"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9998000264167786,"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/T14117","display_name":"Integrated Circuits and Semiconductor Failure Analysis","score":0.9595000147819519,"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"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9495000243186951,"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/robustness","display_name":"Robustness (evolution)","score":0.8268336057662964},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.71471107006073},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7067633271217346},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5726749300956726},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5321473479270935},{"id":"https://openalex.org/keywords/activity-based-costing","display_name":"Activity-based costing","score":0.5246058702468872},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49166280031204224},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.46374520659446716},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.426433801651001},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.41833579540252686},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4045531749725342},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3741547167301178}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8268336057662964},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.71471107006073},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7067633271217346},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5726749300956726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5321473479270935},{"id":"https://openalex.org/C164624739","wikidata":"https://www.wikidata.org/wiki/Q754331","display_name":"Activity-based costing","level":2,"score":0.5246058702468872},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49166280031204224},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.46374520659446716},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.426433801651001},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.41833579540252686},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4045531749725342},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3741547167301178},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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":2,"locations":[{"id":"pmh:oai:arXiv.org:2302.03523","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2302.03523","pdf_url":"https://arxiv.org/pdf/2302.03523","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2302.03523","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2302.03523","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2302.03523","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2302.03523","pdf_url":"https://arxiv.org/pdf/2302.03523","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.5600000023841858,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4319653905.pdf","grobid_xml":"https://content.openalex.org/works/W4319653905.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2069305492","https://openalex.org/W4385524141","https://openalex.org/W3018979822","https://openalex.org/W4297776111","https://openalex.org/W3026616975","https://openalex.org/W2989784533","https://openalex.org/W4288018014","https://openalex.org/W2996058201","https://openalex.org/W2946347869","https://openalex.org/W3127679336"],"abstract_inverted_index":{"Existing":[0],"deep":[1],"neural":[2],"networks":[3],"(DNNs)":[4],"that":[5,43,56,71,93],"achieve":[6],"state-of-the-art":[7],"(SOTA)":[8],"performance":[9],"on":[10,17,108,149],"both":[11,150],"clean":[12,88,151],"and":[13,39,63,69,77,89,152],"adversarially-perturbed":[14],"images":[15],"rely":[16],"either":[18],"activation":[19],"or":[20,33],"weight":[21],"conditioned":[22],"convolution":[23],"operations.":[24],"However,":[25],"such":[26],"conditional":[27],"learning":[28],"costs":[29],"additional":[30],"multiply-accumulate":[31],"(MAC)":[32],"addition":[34],"operations,":[35],"increasing":[36],"inference":[37],"memory":[38],"compute":[40,76,130],"costs.":[41],"To":[42],"end,":[44],"we":[45,138],"present":[46,139],"a":[47,58,74],"sparse":[48,144],"mixture":[49],"once":[50,62],"for":[51,87],"all":[52],"adversarial":[53,90],"training":[54],"(SMART),":[55],"allows":[57],"model":[59],"to":[60,118,121,146],"train":[61],"then":[64,95],"in-situ":[65],"trade-off":[66],"between":[67],"accuracy":[68],"robustness,":[70],"too":[72],"at":[73],"reduced":[75],"parameter":[78],"overhead.":[79],"In":[80],"particular,":[81],"SMART":[82,117],"develops":[83],"two":[84],"expert":[85],"paths,":[86],"images,":[91],"respectively,":[92],"are":[94],"conditionally":[96],"trained":[97],"via":[98],"respective":[99],"dedicated":[100],"sets":[101],"of":[102],"binary":[103],"sparsity":[104],"masks.":[105],"Extensive":[106],"evaluations":[107],"multiple":[109],"image":[110],"classification":[111],"datasets":[112],"across":[113],"different":[114],"models":[115],"show":[116],"have":[119],"up":[120],"2.72x":[122],"fewer":[123],"non-zero":[124],"parameters":[125],"costing":[126],"proportional":[127],"reduction":[128],"in":[129,142],"overhead,":[131],"while":[132],"yielding":[133],"SOTA":[134],"accuracy-robustness":[135],"trade-off.":[136],"Additionally,":[137],"insightful":[140],"observations":[141],"designing":[143],"masks":[145],"successfully":[147],"condition":[148],"perturbed":[153],"images.":[154]},"counts_by_year":[],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}