{"id":"https://openalex.org/W4404134107","doi":"https://doi.org/10.1145/3649329.3656506","title":"MENDNet: Just-in-time Fault Detection and Mitigation in AI Systems with Uncertainty Quantification and Multi-Exit Networks","display_name":"MENDNet: Just-in-time Fault Detection and Mitigation in AI Systems with Uncertainty Quantification and Multi-Exit Networks","publication_year":2024,"publication_date":"2024-06-23","ids":{"openalex":"https://openalex.org/W4404134107","doi":"https://doi.org/10.1145/3649329.3656506"},"language":"en","primary_location":{"id":"doi:10.1145/3649329.3656506","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3649329.3656506","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 61st ACM/IEEE Design Automation Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3649329.3656506","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066094401","display_name":"Shamik Kundu","orcid":"https://orcid.org/0000-0002-5992-8554"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shamik Kundu","raw_affiliation_strings":["University of Texas at Dallas, Dallas, TX, United States"],"raw_orcid":"https://orcid.org/0000-0002-5992-8554","affiliations":[{"raw_affiliation_string":"University of Texas at Dallas, Dallas, TX, United States","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016858094","display_name":"Mirazul Haque","orcid":"https://orcid.org/0009-0006-6627-7688"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mirazul Haque","raw_affiliation_strings":["University of Texas at Dallas, Dallas, TX, United States"],"raw_orcid":"https://orcid.org/0009-0006-6627-7688","affiliations":[{"raw_affiliation_string":"University of Texas at Dallas, Dallas, TX, United States","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109719660","display_name":"Sanjay Das","orcid":null},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjay Das","raw_affiliation_strings":["University of Texas at Dallas, Richardson, TX, United States"],"raw_orcid":"https://orcid.org/0009-0005-4259-1915","affiliations":[{"raw_affiliation_string":"University of Texas at Dallas, Richardson, TX, United States","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100613524","display_name":"Wei Yang","orcid":"https://orcid.org/0000-0002-5338-7347"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Yang","raw_affiliation_strings":["University of Texas at Dallas, Richardson, TX, United States"],"raw_orcid":"https://orcid.org/0000-0002-5338-7347","affiliations":[{"raw_affiliation_string":"University of Texas at Dallas, Richardson, TX, United States","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066320524","display_name":"Kanad Basu","orcid":"https://orcid.org/0000-0002-6431-7512"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kanad Basu","raw_affiliation_strings":["University of Texas at Dallas, Richardson, TX, United States"],"raw_orcid":"https://orcid.org/0000-0002-6431-7512","affiliations":[{"raw_affiliation_string":"University of Texas at Dallas, Richardson, TX, United States","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5066094401"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":0.631,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.70475093,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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":0.9969000220298767,"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/T10917","display_name":"Smart Grid Security and Resilience","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6300340890884399},{"id":"https://openalex.org/keywords/fault-detection-and-isolation","display_name":"Fault detection and isolation","score":0.5518423914909363},{"id":"https://openalex.org/keywords/fault","display_name":"Fault (geology)","score":0.44711703062057495},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.416967511177063},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3220643997192383},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2828587293624878},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1782049536705017}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6300340890884399},{"id":"https://openalex.org/C152745839","wikidata":"https://www.wikidata.org/wiki/Q5438153","display_name":"Fault detection and isolation","level":3,"score":0.5518423914909363},{"id":"https://openalex.org/C175551986","wikidata":"https://www.wikidata.org/wiki/Q47089","display_name":"Fault (geology)","level":2,"score":0.44711703062057495},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.416967511177063},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3220643997192383},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2828587293624878},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1782049536705017},{"id":"https://openalex.org/C165205528","wikidata":"https://www.wikidata.org/wiki/Q83371","display_name":"Seismology","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C172707124","wikidata":"https://www.wikidata.org/wiki/Q423488","display_name":"Actuator","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3649329.3656506","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3649329.3656506","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 61st ACM/IEEE Design Automation Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3649329.3656506","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3649329.3656506","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 61st ACM/IEEE Design Automation Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8600000143051147,"display_name":"Climate action","id":"https://metadata.un.org/sdg/13"}],"awards":[{"id":"https://openalex.org/G5294423750","display_name":null,"funder_award_id":"3243.001","funder_id":"https://openalex.org/F4320306087","funder_display_name":"Semiconductor Research Corporation"},{"id":"https://openalex.org/G6210984941","display_name":null,"funder_award_id":"CNS 2235137","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8422747104","display_name":null,"funder_award_id":"CCF 2146443","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"},{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W3002446690","https://openalex.org/W3075036515","https://openalex.org/W3090586977","https://openalex.org/W3131039502","https://openalex.org/W3162727751","https://openalex.org/W4321608010","https://openalex.org/W4379115629"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2078455782"],"abstract_inverted_index":{"Hardware":[0],"faults":[1,136],"in":[2,6,62,78,82,116,132,137,161,176],"AI":[3,79,174],"accelerators,":[4],"particularly":[5],"accelerator":[7,175],"memory,":[8],"can":[9,127],"alter":[10],"pre-trained":[11],"deep":[12,63],"neural":[13,64,100],"network":[14],"parameters,":[15],"leading":[16],"to":[17,84,158],"errors":[18],"that":[19],"compromise":[20],"performance.":[21],"To":[22,53],"address":[23],"this,":[24],"just-intime":[25],"(JIT)":[26],"fault":[27,35,75,149],"detection":[28,76],"and":[29,73,119,146],"mitigation":[30],"are":[31],"crucial.":[32],"However,":[33],"existing":[34],"detection/mitigation":[36],"approaches,":[37],"either":[38],"interrupt":[39],"continuous":[40],"execution":[41],"or":[42],"introduce":[43],"significant":[44],"latency,":[45],"making":[46],"them":[47],"less":[48],"ideal":[49],"for":[50,114],"JIT":[51],"implementation.":[52],"circumvent":[54],"this":[55,57],"issue,":[56],"paper":[58],"explores":[59],"uncertainty":[60,106,123],"quantification":[61,107,124],"networks":[65],"as":[66],"a":[67,164],"means":[68],"of":[69,88,98,135,172],"facilitating":[70],"an":[71],"efficient":[72],"novel":[74],"approach":[77,155],"accelerators.":[80],"Furthermore,":[81],"order":[83],"mitigate":[85],"the":[86,96,104,111,121,133,138,170,173],"impact":[87],"such":[89],"faults,":[90],"we":[91],"propose":[92],"MENDNet,":[93],"which":[94],"leverages":[95],"properties":[97],"multi-exit":[99],"networks,":[101],"coupled":[102],"with":[103,147],"proposed":[105,154],"framework.":[108],"By":[109],"tuning":[110],"confidence":[112],"threshold":[113],"inference":[115],"each":[117],"exit":[118],"leveraging":[120],"energy-based":[122],"metric,":[125],"MENDNet":[126],"make":[128],"accurate":[129],"predictions":[130],"even":[131],"presence":[134],"accelerator.":[139],"When":[140],"evaluated":[141],"on":[142],"state-of-the-art":[143],"network-dataset":[144],"configurations":[145],"multiple":[148],"rate-fault":[150],"position":[151],"combinations,":[152],"our":[153],"furnishes":[156],"up":[157],"80.42%":[159],"improvement":[160],"accuracy":[162],"over":[163],"traditional":[165],"DNN":[166],"implementation,":[167],"thereby":[168],"instilling":[169],"reliability":[171],"mission":[177],"mode.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}
