{"id":"https://openalex.org/W3008334662","doi":"https://doi.org/10.1109/bigdata47090.2019.9006466","title":"Diagnosis of Neural Network via Backward Deduction","display_name":"Diagnosis of Neural Network via Backward Deduction","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3008334662","doi":"https://doi.org/10.1109/bigdata47090.2019.9006466","mag":"3008334662"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata47090.2019.9006466","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata47090.2019.9006466","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5049036241","display_name":"Peifeng Yin","orcid":"https://orcid.org/0000-0002-0109-7903"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peifeng Yin","raw_affiliation_strings":["IBM Research - Almaden, San Jose, US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - Almaden, San Jose, US","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100784430","display_name":"Lei Huang","orcid":"https://orcid.org/0000-0003-4087-3677"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Huang","raw_affiliation_strings":["IBM Research - Almaden, San Jose, US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - Almaden, San Jose, US","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052606390","display_name":"\uc774\uc21c\ud658","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sunhwan Lee","raw_affiliation_strings":["IBM Research - Almaden, San Jose, US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - Almaden, San Jose, US","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101954414","display_name":"Mu Qiao","orcid":"https://orcid.org/0000-0001-7309-4237"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mu Qiao","raw_affiliation_strings":["IBM Research - Almaden, San Jose, US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - Almaden, San Jose, US","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065749078","display_name":"Shubhi Asthana","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shubhi Asthana","raw_affiliation_strings":["IBM Research - Almaden, San Jose, US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - Almaden, San Jose, US","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039308580","display_name":"Tagiga Nakamura","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tagiga Nakamura","raw_affiliation_strings":["IBM Research - Almaden, San Jose, US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - Almaden, San Jose, US","institution_ids":["https://openalex.org/I4210085935"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210085935"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"260","last_page":"267"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9997000098228455,"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":0.9997000098228455,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9997000098228455,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9886999726295471,"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/interpretability","display_name":"Interpretability","score":0.9636884927749634},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7703823447227478},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.7070208191871643},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6018438339233398},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5781307220458984},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5371224880218506},{"id":"https://openalex.org/keywords/vulnerability","display_name":"Vulnerability (computing)","score":0.5241204500198364},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4665640890598297},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43091264367103577},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.43024227023124695},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.42993417382240295},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.42830324172973633},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3253183364868164},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14751115441322327}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9636884927749634},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7703823447227478},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.7070208191871643},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6018438339233398},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5781307220458984},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5371224880218506},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.5241204500198364},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4665640890598297},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43091264367103577},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.43024227023124695},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.42993417382240295},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.42830324172973633},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3253183364868164},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14751115441322327},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"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/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata47090.2019.9006466","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata47090.2019.9006466","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1787224781","https://openalex.org/W1849277567","https://openalex.org/W1945616565","https://openalex.org/W2060642394","https://openalex.org/W2112796928","https://openalex.org/W2180612164","https://openalex.org/W2195388612","https://openalex.org/W2198606573","https://openalex.org/W2282821441","https://openalex.org/W2346578521","https://openalex.org/W2594633041","https://openalex.org/W2605409611","https://openalex.org/W2766047647","https://openalex.org/W2773497437","https://openalex.org/W2787070805","https://openalex.org/W2809671526","https://openalex.org/W2949725973","https://openalex.org/W2951885001","https://openalex.org/W2962851944","https://openalex.org/W2962862931","https://openalex.org/W2963207607","https://openalex.org/W2963208207","https://openalex.org/W2963276306","https://openalex.org/W2979200397","https://openalex.org/W4251868557","https://openalex.org/W4293507378","https://openalex.org/W4295313945","https://openalex.org/W6639204139","https://openalex.org/W6640425456","https://openalex.org/W6685133223","https://openalex.org/W6704488215","https://openalex.org/W6734194636","https://openalex.org/W6736518430","https://openalex.org/W6737947904","https://openalex.org/W6745027582","https://openalex.org/W6746876212","https://openalex.org/W6748281036","https://openalex.org/W6748744355","https://openalex.org/W6754719772"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W2888392564","https://openalex.org/W4319993887","https://openalex.org/W4297789176","https://openalex.org/W2768346313","https://openalex.org/W2963249138","https://openalex.org/W2998594699","https://openalex.org/W4396882122","https://openalex.org/W3178016723","https://openalex.org/W2968060152"],"abstract_inverted_index":{"Although":[0],"widely":[1],"used":[2],"in":[3,83,102,122],"various":[4],"areas,":[5],"the":[6,12,25,70,73,76,84,91,103,124,127,134],"Deep":[7],"Neural":[8],"Network":[9],"suffers":[10],"from":[11,112],"lack":[13],"of":[14,37,45,51],"interpretability.":[15],"Existing":[16],"works":[17],"usually":[18],"focus":[19],"on":[20,69,90],"one":[21],"data":[22,81,111,125,130],"instance":[23],"and":[24,48],"found":[26],"explanations":[27,44],"are":[28,97],"thus":[29],"limited.":[30],"We":[31],"argue":[32],"that":[33,118],"a":[34,38,67],"good":[35],"understanding":[36],"model":[39,46,71,135],"should":[40],"contain":[41],"both":[42],"systematic":[43],"behavior":[47],"effective":[49],"detection":[50],"its":[52,138],"vulnerability.":[53,139],"Particularly":[54],"we":[55,116],"propose":[56],"to":[57,61,78],"use":[58],"backward":[59],"deduction":[60,74],"achieve":[62],"these":[63],"two":[64],"goals.":[65],"Given":[66],"constraint":[68],"output,":[72],"backtracks":[75],"architecture":[77],"find":[79],"corresponding":[80],"ranges":[82,101],"input.":[85],"In":[86,114],"each":[87],"layer,":[88],"depending":[89],"type,":[92],"specific":[93],"rules":[94],"and/or":[95],"algorithms":[96],"developed.":[98],"The":[99],"resulted":[100],"end":[104],"can":[105,131],"be":[106],"interpreted":[107],"by":[108],"sampling":[109],"exemplary":[110],"them.":[113],"experiment":[115],"show":[117],"with":[119],"different":[120],"strategies":[121],"selecting":[123],"ranges,":[126],"sampled":[128],"fake":[129],"either":[132],"explain":[133],"or":[136],"reflect":[137]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}