{"id":"https://openalex.org/W3202425151","doi":"https://doi.org/10.1109/iccv48922.2021.00516","title":"HIRE-SNN: Harnessing the Inherent Robustness of Energy-Efficient Deep Spiking Neural Networks by Training with Crafted Input Noise","display_name":"HIRE-SNN: Harnessing the Inherent Robustness of Energy-Efficient Deep Spiking Neural Networks by Training with Crafted Input Noise","publication_year":2021,"publication_date":"2021-10-01","ids":{"openalex":"https://openalex.org/W3202425151","doi":"https://doi.org/10.1109/iccv48922.2021.00516","mag":"3202425151"},"language":"en","primary_location":{"id":"doi:10.1109/iccv48922.2021.00516","doi":"https://doi.org/10.1109/iccv48922.2021.00516","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv48922.2021.00516","pdf_url":null,"source":{"id":"https://openalex.org/S4363607764","display_name":"IEEE/CVF International Conference on Computer Vision (ICCV)","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2110.11417","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076002956","display_name":"Souvik Kundu","orcid":"https://orcid.org/0000-0002-3533-9405","observed_orcids":["https://orcid.org/0000-0002-3533-9405"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Souvik Kundu","raw_affiliation_strings":["University of Southern California,Los Angeles,CA,USA","University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044650311","display_name":"Massoud Pedram","orcid":"https://orcid.org/0000-0002-2677-7307","observed_orcids":["https://orcid.org/0000-0002-2677-7307"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Massoud Pedram","raw_affiliation_strings":["University of Southern California,Los Angeles,CA,USA","University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084205024","display_name":"Peter A. Beerel","orcid":"https://orcid.org/0000-0002-8283-0168","observed_orcids":["https://orcid.org/0000-0002-8283-0168"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter A. Beerel","raw_affiliation_strings":["University of Southern California,Los Angeles,CA,USA","University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":4.8512,"has_fulltext":true,"cited_by_count":76,"citation_normalized_percentile":{"value":0.96272025,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5189","last_page":"5198"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9750999808311462,"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":0.9750999808311462,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.0071000000461936,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0015999999595806003,"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/deep-spiking-neural-networks","display_name":"deep spiking neural networks","score":0.9610000252723694},{"id":"https://openalex.org/keywords/adversarial-robustness","display_name":"adversarial robustness","score":0.9629999995231628},{"id":"https://openalex.org/keywords/fgsm","display_name":"FGSM","score":0.8240000009536743},{"id":"https://openalex.org/keywords/projected-gradient-descent","display_name":"projected gradient descent","score":0.9869999885559082},{"id":"https://openalex.org/keywords/snn-training","display_name":"SNN training","score":0.6370000243186951},{"id":"https://openalex.org/keywords/energy-efficient-neural-networks","display_name":"energy-efficient neural networks","score":0.6840000152587891},{"id":"https://openalex.org/keywords/neuromorphic-hardware","display_name":"neuromorphic hardware","score":0.8109999895095825},{"id":"https://openalex.org/keywords/low-latency-classification","display_name":"low-latency classification","score":0.703000009059906},{"id":"https://openalex.org/keywords/cifar-10","display_name":"CIFAR-10","score":0.8309999704360962},{"id":"https://openalex.org/keywords/cifar-100","display_name":"CIFAR-100","score":1.0}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8307174444198608},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7898229360580444},{"id":"https://openalex.org/C11731999","wikidata":"https://www.wikidata.org/wiki/Q9067355","display_name":"Spiking neural network","level":3,"score":0.742702841758728},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6274852156639099},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5805360078811646},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5616628527641296},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5039398074150085},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.45004165172576904},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4285376965999603},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.41664204001426697},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.41465023159980774},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.396495521068573},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iccv48922.2021.00516","doi":"https://doi.org/10.1109/iccv48922.2021.00516","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv48922.2021.00516","pdf_url":null,"source":{"id":"https://openalex.org/S4363607764","display_name":"IEEE/CVF International Conference on Computer Vision (ICCV)","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2110.11417","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.11417","pdf_url":"https://arxiv.org/pdf/2110.11417","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},{"id":"mag:3211011078","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2110.11417.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2110.11417","doi":"https://doi.org/10.48550/arxiv.2110.11417","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2110.11417","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2110.11417","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.11417","pdf_url":"https://arxiv.org/pdf/2110.11417","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Affordable and clean energy","score":0.8399999737739563,"id":"https://metadata.un.org/sdg/7"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G1881860044","display_name":"SHF: Medium: Training Sparse Neural Networks with Co-Designed Hardware Accelerators: Enabling Model Optimization and Scientific Exploration","funder_award_id":"1763747","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3202425151.pdf","grobid_xml":"https://content.openalex.org/works/W3202425151.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1645800954","https://openalex.org/W1686810756","https://openalex.org/W1945616565","https://openalex.org/W1979974160","https://openalex.org/W1999085092","https://openalex.org/W2007339694","https://openalex.org/W2058582133","https://openalex.org/W2062899906","https://openalex.org/W2097117768","https://openalex.org/W2194775991","https://openalex.org/W2243397390","https://openalex.org/W2570343428","https://openalex.org/W2604505099","https://openalex.org/W2621826044","https://openalex.org/W2746600820","https://openalex.org/W2786965798","https://openalex.org/W2787708942","https://openalex.org/W2807807191","https://openalex.org/W2898323475","https://openalex.org/W2899771611","https://openalex.org/W2940648411","https://openalex.org/W2946498182","https://openalex.org/W2963485691","https://openalex.org/W2984844508","https://openalex.org/W3003531906","https://openalex.org/W3007283957","https://openalex.org/W3007926765","https://openalex.org/W3012743867","https://openalex.org/W3026873071","https://openalex.org/W3047826181","https://openalex.org/W3110857671","https://openalex.org/W3118608800","https://openalex.org/W3120485781","https://openalex.org/W3121127024","https://openalex.org/W3128829362","https://openalex.org/W3134621603","https://openalex.org/W3185473337","https://openalex.org/W3186531543","https://openalex.org/W4293846201"],"related_works":["https://openalex.org/W2895097035","https://openalex.org/W4206903459","https://openalex.org/W2754816816","https://openalex.org/W4366280654","https://openalex.org/W3160167280","https://openalex.org/W3020853991","https://openalex.org/W4362706668","https://openalex.org/W4231621013","https://openalex.org/W3171021120","https://openalex.org/W3008318776"],"abstract_inverted_index":{"Low-latency":[0],"deep":[1,68],"spiking":[2],"neural":[3,14],"networks":[4,15],"(SNNs)":[5],"have":[6,74,230],"become":[7],"a":[8,84],"promising":[9],"alternative":[10],"to":[11,36,44,55,113,162,176,217],"conventional":[12],"artificial":[13],"(ANNs)":[16],"because":[17],"of":[18,67,87,91,142,151,174],"their":[19],"potential":[20],"for":[21,50],"increased":[22],"energy":[23],"efficiency":[24],"on":[25,155,180,202,211],"event-driven":[26],"neuromorphic":[27],"hardware.":[28],"Neural":[29],"networks,":[30],"including":[31],"SNNs,":[32,62,166],"however,":[33],"are":[34],"subject":[35],"various":[37,71],"adversarial":[38,72],"attacks":[39,49,73,120],"and":[40,65,104,132,153,158,178,182,219,223],"must":[41],"be":[42],"trained":[43,164,168,201],"remain":[45],"resilient":[46],"against":[47,94,118],"such":[48],"many":[51],"applications.":[52],"Nevertheless,":[53],"due":[54],"prohibitively":[56],"high":[57],"training":[58,125,136],"costs":[59],"associated":[60],"with":[61,149,188,205],"an":[63,123],"analysis":[64,86],"optimization":[66],"SNNs":[69,93,200],"under":[70],"been":[75],"largely":[76],"overlooked.":[77],"In":[78],"this":[79,111],"paper,":[80],"we":[81,121,145,229],"first":[82],"present":[83,122],"detailed":[85],"the":[88,115,140,232],"inherent":[89],"robustness":[90,117],"low-latency":[92],"popular":[95],"gradient-based":[96],"attacks,":[97],"namely":[98],"fast":[99],"gradient":[100,106],"sign":[101],"method":[102],"(FGSM)":[103],"projected":[105],"descent":[107],"(PGD).":[108],"Motivated":[109],"by":[110],"analysis,":[112],"harness":[114],"model\u2019s":[116],"these":[119],"SNN":[124],"algorithm":[126],"that":[127],"uses":[128],"crafted":[129],"input":[130],"noise":[131],"incurs":[133],"no":[134],"additional":[135],"time.":[137],"To":[138],"evaluate":[139],"merits":[141],"our":[143,167],"algorithm,":[144],"conducted":[146],"extensive":[147],"experiments":[148],"variants":[150],"VGG":[152],"ResNet":[154],"both":[156],"CIFAR-10":[157],"CIFAR-100":[159],"dataset.":[160],"Compared":[161],"standard":[163],"direct-input":[165],"models":[169,196],"yield":[170],"improved":[171,206],"classification":[172,209],"accuracy":[173],"up":[175,216],"13.7%":[177],"10.1%":[179],"FGSM":[181],"PGD":[183],"attack":[184],"generated":[185],"images,":[186],"respectively,":[187],"negligible":[189],"loss":[190],"in":[191],"clean":[192],"image":[193],"accuracy.":[194],"Our":[195],"also":[197],"outperform":[198],"inherently-robust":[199],"rate-coded":[203],"inputs":[204],"or":[207],"similar":[208],"performance":[210],"attack-generated":[212],"images":[213],"while":[214],"having":[215],"25\u00d7":[218],"\u223c4.6\u00d7":[220],"lower":[221],"latency":[222],"computation":[224],"energy,":[225],"respectively.":[226],"For":[227],"reproducibility,":[228],"open-sourced":[231],"code":[233],"at":[234],"github.com/ksouvik52/hiresnn2021.":[235]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":23},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":11}],"updated_date":"2026-10-21T09:56:26.102985","created_date":"2025-10-10T00:00:00"}