{"id":"https://openalex.org/W2964187630","doi":"https://doi.org/10.1109/bigdata.2017.8258029","title":"Contaminant removal for Android malware detection systems","display_name":"Contaminant removal for Android malware detection systems","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2964187630","doi":"https://doi.org/10.1109/bigdata.2017.8258029","mag":"2964187630"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2017.8258029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2017.8258029","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Big Data (Big Data)","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/A5015105117","display_name":"Lichao Sun","orcid":"https://orcid.org/0000-0003-1539-7939"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lichao Sun","raw_affiliation_strings":["University of Illinois at Chicago, Chicago, IL"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Chicago, Chicago, IL","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085706537","display_name":"Xiaokai Wei","orcid":"https://orcid.org/0000-0003-2749-7419"},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaokai Wei","raw_affiliation_strings":["Facebook, Menlo Park, CA"],"affiliations":[{"raw_affiliation_string":"Facebook, Menlo Park, CA","institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100462845","display_name":"Jiawei Zhang","orcid":"https://orcid.org/0000-0002-8634-1687"},"institutions":[{"id":"https://openalex.org/I103163165","display_name":"Florida State University","ror":"https://ror.org/05g3dte14","country_code":"US","type":"education","lineage":["https://openalex.org/I103163165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiawei Zhang","raw_affiliation_strings":["IFM Lab, Florida State University, FL"],"affiliations":[{"raw_affiliation_string":"IFM Lab, Florida State University, FL","institution_ids":["https://openalex.org/I103163165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071709543","display_name":"Lifang He","orcid":"https://orcid.org/0000-0001-7810-9071"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lifang He","raw_affiliation_strings":["Cornell University, New York City, NY"],"affiliations":[{"raw_affiliation_string":"Cornell University, New York City, NY","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036357902","display_name":"Philip S. Yu","orcid":"https://orcid.org/0000-0002-3491-5968"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Philip S. Yu","raw_affiliation_strings":["University of Illinois at Chicago, Chicago, IL"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Chicago, Chicago, IL","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038574274","display_name":"Witawas Srisa\u2010an","orcid":"https://orcid.org/0000-0003-0021-5696"},"institutions":[{"id":"https://openalex.org/I114395901","display_name":"University of Nebraska\u2013Lincoln","ror":"https://ror.org/043mer456","country_code":"US","type":"education","lineage":["https://openalex.org/I114395901"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Witawas Srisa-an","raw_affiliation_strings":["University of Nebraska-Lincoln, Lincoln, NE"],"affiliations":[{"raw_affiliation_string":"University of Nebraska-Lincoln, Lincoln, NE","institution_ids":["https://openalex.org/I114395901"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5015105117"],"corresponding_institution_ids":["https://openalex.org/I39422238"],"apc_list":null,"apc_paid":null,"fwci":1.8492,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.87545712,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1053","last_page":"1062"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.991599977016449,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9908999800682068,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/malware","display_name":"Malware","score":0.8714509010314941},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8384198546409607},{"id":"https://openalex.org/keywords/upload","display_name":"Upload","score":0.6326220035552979},{"id":"https://openalex.org/keywords/android","display_name":"Android (operating system)","score":0.6289332509040833},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5322052836418152},{"id":"https://openalex.org/keywords/android-malware","display_name":"Android malware","score":0.5283385515213013},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4949464201927185},{"id":"https://openalex.org/keywords/false-positive-rate","display_name":"False positive rate","score":0.43576693534851074},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.30490607023239136},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14353728294372559}],"concepts":[{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.8714509010314941},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8384198546409607},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.6326220035552979},{"id":"https://openalex.org/C557433098","wikidata":"https://www.wikidata.org/wiki/Q94","display_name":"Android (operating system)","level":2,"score":0.6289332509040833},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5322052836418152},{"id":"https://openalex.org/C2989133298","wikidata":"https://www.wikidata.org/wiki/Q94","display_name":"Android malware","level":3,"score":0.5283385515213013},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4949464201927185},{"id":"https://openalex.org/C95922358","wikidata":"https://www.wikidata.org/wiki/Q5432725","display_name":"False positive rate","level":2,"score":0.43576693534851074},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.30490607023239136},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14353728294372559}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2017.8258029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2017.8258029","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1619480882","https://openalex.org/W1856835768","https://openalex.org/W1964241047","https://openalex.org/W2011256616","https://openalex.org/W2022580894","https://openalex.org/W2037026906","https://openalex.org/W2041276426","https://openalex.org/W2044849491","https://openalex.org/W2122672392","https://openalex.org/W2123958887","https://openalex.org/W2134510195","https://openalex.org/W2295156440","https://openalex.org/W2510343936","https://openalex.org/W2575006718","https://openalex.org/W2600788550","https://openalex.org/W2621677039","https://openalex.org/W2626320814","https://openalex.org/W2739085552","https://openalex.org/W2739547565","https://openalex.org/W2767768667","https://openalex.org/W2782618046","https://openalex.org/W2963014045","https://openalex.org/W2963674136","https://openalex.org/W6739514449","https://openalex.org/W6742101474"],"related_works":["https://openalex.org/W2782775281","https://openalex.org/W2560361988","https://openalex.org/W2507113366","https://openalex.org/W2591124010","https://openalex.org/W3200508744","https://openalex.org/W3025122950","https://openalex.org/W2311926078","https://openalex.org/W2895504842","https://openalex.org/W2717179875","https://openalex.org/W4249118297"],"abstract_inverted_index":{"A":[0],"recent":[1],"report":[2],"indicates":[3],"that":[4,227],"there":[5],"is":[6],"a":[7,185,194],"new":[8],"malicious":[9,30,63],"app":[10,42],"introduced":[11],"every":[12],"4":[13],"seconds.":[14],"This":[15],"rapid":[16],"malware":[17,22,148,165,240],"distribution":[18],"rate":[19,242],"causes":[20],"existing":[21],"detection":[23,81,133,149,202,207,241,244],"systems":[24,208],"to":[25,32,65,152,169,189,215],"fall":[26],"far":[27],"behind,":[28],"allowing":[29,161],"apps":[31,64,87,103],"escape":[33],"vetting":[34],"efforts":[35],"and":[36,67,73,88,116,129,134,145,154,167,173,204,218,243],"be":[37,170],"distributed":[38],"by":[39],"even":[40],"legitimate":[41],"stores.":[43],"When":[44],"trusted":[45],"downloading":[46],"sites":[47,59],"distribute":[48],"malware,":[49],"several":[50],"negative":[51],"consequences":[52],"ensue.":[53],"First,":[54],"the":[55,127,178,201,219,233],"popularity":[56],"of":[57,109,120,131,180,196,206],"these":[58,86],"would":[60],"allow":[61],"such":[62,181],"quickly":[66],"widely":[68],"infect":[69],"devices.":[70],"Second,":[71],"analysts":[72],"researchers":[74],"who":[75],"rely":[76],"on":[77],"machine":[78,162],"learning":[79,163],"based":[80,164],"techniques":[82],"may":[83],"also":[84],"download":[85],"mistakenly":[89],"label":[90],"them":[91],"as":[92,100,107],"benign":[93,111,123],"since":[94],"they":[95],"have":[96],"not":[97],"been":[98],"disclosed":[99],"malware.":[101],"These":[102],"are":[104],"then":[105,199],"used":[106],"part":[108],"their":[110,132],"dataset":[112,124],"during":[113],"model":[114],"training":[115,159],"testing.":[117],"The":[118,224],"presence":[119],"contaminants":[121,157,217,231],"in":[122],"can":[125,236],"compromise":[126],"effectiveness":[128],"accuracy":[130,205],"classification":[135],"techniques.":[136],"To":[137,175],"address":[138],"this":[139],"issue,":[140],"we":[141,183,229,235],"introduce":[142],"PUDROID":[143,214],"(Positive":[144],"Unlabeled":[146],"learning-based":[147],"for":[150],"Android)":[151],"automatically":[153],"effectively":[155],"remove":[156,216,230],"from":[158,193,232],"datasets,":[160,234],"classifiers":[166],"detectors":[168],"more":[171],"effective":[172],"accurate.":[174],"further":[176],"improve":[177,238],"performance":[179],"detectors,":[182],"apply":[184],"feature":[186],"selection":[187],"strategy":[188],"select":[190],"pertinent":[191],"features":[192],"variety":[195],"features.":[197],"We":[198],"compare":[200],"rates":[203],"using":[209,213],"two":[210],"datasets;":[211],"one":[212],"other":[220],"without":[221],"removing":[222],"contaminants.":[223],"results":[225],"indicate":[226],"once":[228],"significantly":[237],"both":[239],"accuracy.":[245]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}