{"id":"https://openalex.org/W2921624216","doi":"https://doi.org/10.1109/malware.2018.8659362","title":"Resilience of Pruned Neural Network Against Poisoning Attack","display_name":"Resilience of Pruned Neural Network Against Poisoning Attack","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2921624216","doi":"https://doi.org/10.1109/malware.2018.8659362","mag":"2921624216"},"language":"en","primary_location":{"id":"doi:10.1109/malware.2018.8659362","is_oa":false,"landing_page_url":"https://doi.org/10.1109/malware.2018.8659362","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 13th International Conference on Malicious and Unwanted Software (MALWARE)","raw_type":"proceedings-article"},"type":"article","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/A5085461777","display_name":"Bingyin Zhao","orcid":"https://orcid.org/0000-0003-0372-8198"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bingyin Zhao","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Clemson University, Clemson, SC 29634"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Clemson University, Clemson, SC 29634","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071172709","display_name":"Yingjie Lao","orcid":"https://orcid.org/0000-0002-9413-2455"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yingjie Lao","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Clemson University, Clemson, SC 29634"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Clemson University, Clemson, SC 29634","institution_ids":["https://openalex.org/I8078737"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5069,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.75646268,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"78","last_page":"83"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":1.0,"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":1.0,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9994000196456909,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9847999811172485,"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/resilience","display_name":"Resilience (materials science)","score":0.8100044131278992},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7151802778244019},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.5555840730667114},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5469433069229126},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3012203276157379}],"concepts":[{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.8100044131278992},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7151802778244019},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.5555840730667114},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5469433069229126},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3012203276157379},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/malware.2018.8659362","is_oa":false,"landing_page_url":"https://doi.org/10.1109/malware.2018.8659362","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 13th International Conference on Malicious and Unwanted Software (MALWARE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1673923490","https://openalex.org/W1945616565","https://openalex.org/W1966948031","https://openalex.org/W2057175746","https://openalex.org/W2095577883","https://openalex.org/W2103154003","https://openalex.org/W2103753221","https://openalex.org/W2109343507","https://openalex.org/W2112507308","https://openalex.org/W2119112357","https://openalex.org/W2125908420","https://openalex.org/W2133564696","https://openalex.org/W2149933564","https://openalex.org/W2161381512","https://openalex.org/W2163605009","https://openalex.org/W2325939864","https://openalex.org/W2399587145","https://openalex.org/W2516373086","https://openalex.org/W2557044351","https://openalex.org/W2561975083","https://openalex.org/W2581082771","https://openalex.org/W2591602089","https://openalex.org/W2613718673","https://openalex.org/W2618043096","https://openalex.org/W2771111398","https://openalex.org/W2772825438","https://openalex.org/W2774423163","https://openalex.org/W2807363941","https://openalex.org/W2902931196","https://openalex.org/W2962763344","https://openalex.org/W2963165448","https://openalex.org/W2963207607","https://openalex.org/W2963542245","https://openalex.org/W2963564844","https://openalex.org/W2963674932","https://openalex.org/W2964043980","https://openalex.org/W2964082701","https://openalex.org/W2964153729","https://openalex.org/W2964308564","https://openalex.org/W3103940881","https://openalex.org/W4252979261","https://openalex.org/W4299518610","https://openalex.org/W4394644156","https://openalex.org/W6620707391","https://openalex.org/W6637162671","https://openalex.org/W6640425456","https://openalex.org/W6676935882","https://openalex.org/W6679434410","https://openalex.org/W6682132143","https://openalex.org/W6684191040","https://openalex.org/W6700903540","https://openalex.org/W6712837096","https://openalex.org/W6719080892","https://openalex.org/W6726264252","https://openalex.org/W6730054736","https://openalex.org/W6734354522","https://openalex.org/W6746576367","https://openalex.org/W6746897123","https://openalex.org/W6864546407"],"related_works":["https://openalex.org/W2386387936","https://openalex.org/W2083519861","https://openalex.org/W4292730478","https://openalex.org/W2364538711","https://openalex.org/W3195375806","https://openalex.org/W3017579772","https://openalex.org/W1629725936","https://openalex.org/W3007967230","https://openalex.org/W2030496847","https://openalex.org/W3001020386"],"abstract_inverted_index":{"In":[0,52],"the":[1,40,49,57,63,77,85,91,100,106,121,133],"past":[2],"several":[3],"years,":[4],"machine":[5,24],"learning,":[6,9],"especially":[7],"deep":[8],"has":[10,19],"achieved":[11],"remarkable":[12],"success":[13],"in":[14,38,90,96],"various":[15],"fields.":[16],"However,":[17],"it":[18],"been":[20],"shown":[21],"recently":[22],"that":[23,72],"learning":[25],"algorithms":[26],"are":[27,118,130],"vulnerable":[28],"to":[29,84,98],"well-crafted":[30],"attacks.":[31,67],"For":[32,94],"instance,":[33],"poisoning":[34,66,80,116],"attack":[35],"is":[36],"effective":[37],"manipulating":[39],"results":[41,70],"of":[42,59,79,88],"a":[43],"predictive":[44],"model":[45],"by":[46],"deliberately":[47],"contaminating":[48],"training":[50],"data.":[51],"this":[53],"paper,":[54],"we":[55],"investigate":[56],"implication":[58],"network":[60],"pruning":[61,73],"on":[62],"resilience":[64],"against":[65],"Our":[68],"experimental":[69],"show":[71],"can":[74],"effectively":[75],"increase":[76],"difficulty":[78],"attack,":[81],"possibly":[82],"due":[83],"reduced":[86],"degrees":[87],"freedom":[89],"pruned":[92,137],"network.":[93],"example,":[95],"order":[97],"degrade":[99],"test":[101],"accuracy":[102],"below":[103],"60%":[104],"for":[105,120,132],"MNIST-1-7":[107],"dataset,":[108],"only":[109],"less":[110],"than":[111],"10":[112],"retraining":[113],"epochs":[114,129],"with":[115],"data":[117],"needed":[119],"original":[122],"network,":[123],"while":[124],"about":[125],"16":[126],"and":[127,135],"40":[128],"required":[131],"90%":[134],"99%":[136],"networks,":[138],"respectively.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}