{"id":"https://openalex.org/W3217279074","doi":"https://doi.org/10.1109/apcc49754.2021.9609892","title":"Duplicates in the Drebin Dataset and Reduction in the Accuracy of the Malware Detection Models","display_name":"Duplicates in the Drebin Dataset and Reduction in the Accuracy of the Malware Detection Models","publication_year":2021,"publication_date":"2021-10-11","ids":{"openalex":"https://openalex.org/W3217279074","doi":"https://doi.org/10.1109/apcc49754.2021.9609892","mag":"3217279074"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/apcc49754.2021.9609892","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5021553021","display_name":"Jyotiprakash Mishra","orcid":"https://orcid.org/0000-0001-7590-1215"},"institutions":[{"id":"https://openalex.org/I67357951","display_name":"KIIT University","ror":"https://ror.org/00k8zt527","country_code":"IN","type":"education","lineage":["https://openalex.org/I67357951"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Jyotiprakash Mishra","raw_affiliation_strings":["School of Computer Engineering, Kalinga Institute of Industrial Technology, Bhubaneswar, India"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Kalinga Institute of Industrial Technology, Bhubaneswar, India","institution_ids":["https://openalex.org/I67357951"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053903379","display_name":"Sanjay K. Sahay","orcid":"https://orcid.org/0000-0002-4640-2107"},"institutions":[{"id":"https://openalex.org/I4210148827","display_name":"Birla Institute of Technology and Science, Pilani - Goa Campus","ror":"https://ror.org/046sh6j17","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210148827","https://openalex.org/I74796645"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sanjay K. Sahay","raw_affiliation_strings":["Dept. of Computer Science & Information Systems, BITS Pilani, K. K. Birla Goa Campus, Goa, India"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science & Information Systems, BITS Pilani, K. K. Birla Goa Campus, Goa, India","institution_ids":["https://openalex.org/I4210148827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023050538","display_name":"Hemant Rathore","orcid":"https://orcid.org/0000-0001-7298-0210"},"institutions":[{"id":"https://openalex.org/I4210148827","display_name":"Birla Institute of Technology and Science, Pilani - Goa Campus","ror":"https://ror.org/046sh6j17","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210148827","https://openalex.org/I74796645"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hemant Rathore","raw_affiliation_strings":["Dept. of Computer Science & Information Systems, BITS Pilani, K. K. Birla Goa Campus, Goa, India"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science & Information Systems, BITS Pilani, K. K. Birla Goa Campus, Goa, India","institution_ids":["https://openalex.org/I4210148827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005921539","display_name":"Lokesh Kumar","orcid":"https://orcid.org/0000-0001-6167-9625"},"institutions":[{"id":"https://openalex.org/I4210148827","display_name":"Birla Institute of Technology and Science, Pilani - Goa Campus","ror":"https://ror.org/046sh6j17","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210148827","https://openalex.org/I74796645"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Lokesh Kumar","raw_affiliation_strings":["Dept. of Computer Science & Information Systems, BITS Pilani, K. K. Birla Goa Campus, Goa, India"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science & Information Systems, BITS Pilani, K. K. Birla Goa Campus, Goa, India","institution_ids":["https://openalex.org/I4210148827"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.42,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.528875,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":72,"max":76},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":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":0.9926,"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/T12034","display_name":"Digital and Cyber Forensics","score":0.9868,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/opcode","display_name":"Opcode","score":0.92812663}],"concepts":[{"id":"https://openalex.org/C52173422","wikidata":"https://www.wikidata.org/wiki/Q766483","display_name":"Opcode","level":2,"score":0.92812663},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.83154315},{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.8087747},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.72266996},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6334641},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6198558},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5359937},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47586244},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4674837},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4587406},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.45670885},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.14424148},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08259484}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/apcc49754.2021.9609892","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.72,"display_name":"Peace, justice, and strong institutions","id":"https://metadata.un.org/sdg/16"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":24,"referenced_works":["https://openalex.org/W2003791967","https://openalex.org/W2051725773","https://openalex.org/W2079215333","https://openalex.org/W2100151287","https://openalex.org/W2122672392","https://openalex.org/W2146667387","https://openalex.org/W2468505451","https://openalex.org/W2531260576","https://openalex.org/W2732916693","https://openalex.org/W2795678871","https://openalex.org/W2886383271","https://openalex.org/W2913493033","https://openalex.org/W2955343150","https://openalex.org/W3026718724","https://openalex.org/W3086404086","https://openalex.org/W3092522462","https://openalex.org/W3093436843","https://openalex.org/W3104307515","https://openalex.org/W3106196258","https://openalex.org/W3126643594","https://openalex.org/W3126999556","https://openalex.org/W3135411660","https://openalex.org/W3135701003","https://openalex.org/W36091977"],"related_works":["https://openalex.org/W4316087074","https://openalex.org/W4294067781","https://openalex.org/W4283784365","https://openalex.org/W4283016678","https://openalex.org/W4249229055","https://openalex.org/W3211546796","https://openalex.org/W3204641204","https://openalex.org/W3106196258","https://openalex.org/W2968586400","https://openalex.org/W2942650110"],"abstract_inverted_index":{"The":[0,140,199],"Android":[1],"operating":[2],"system":[3],"has":[4],"constantly":[5],"remained":[6],"in":[7,86,102,159,204,208,245],"the":[8,12,17,31,51,82,87,91,103,114,117,127,147,152,180,209,215,221,226],"limelight,":[9],"hence":[10],"attracts":[11],"attention":[13],"of":[14,33,50,53,68,93,116,146,225,248],"cyber-criminals.":[15],"Understanding":[16],"rising":[18],"challenges,":[19],"many":[20],"researchers":[21],"have":[22,64,105],"bagged":[23],"achievements":[24],"by":[25,133,161,173,218],"applying":[26],"machine/deep":[27],"learning":[28],"techniques":[29],"for":[30],"construction":[32],"malware":[34,41,227],"detection":[35,119,228],"models":[36,120,229],"based":[37,230],"on":[38,90,231],"popular":[39,118,149],"Drebin":[40,88,232],"datasets.":[42],"However,":[43],"a":[44,48,65,75,157,242],"cursory":[45],"look":[46],"at":[47],"table":[49],"frequency":[52],"Dalvik":[54],"opcodes":[55,94],"leads":[56],"us":[57],"to":[58,80,241],"believe":[59],"that":[60,98,144],"this":[61,246],"dataset":[62],"may":[63,239],"massive":[66],"number":[67],"duplicate":[69,83],"malicious":[70,84,100],"files.":[71],"Hence,":[72,110],"we":[73,112,183],"used":[74],"technique":[76],"called":[77],"fitting":[78],"factor":[79],"find":[81],"files":[85],"datasets":[89,104],"basis":[92],"occurrence.":[95],"We":[96],"found":[97],"51.57%":[99],"samples":[101],"one":[106,145],"or":[107],"more":[108],"duplicates.":[109],"accordingly,":[111],"studied":[113],"performance":[115,224],"with":[121,125,166,187,214],"and":[122,137,164,175,195,236],"without":[123],"duplicates":[124],"all":[126,167],"features,":[128,168],"top":[129,169],"26":[130,170],"features":[131,171,216],"engineered":[132],"Information":[134],"Gain":[135],"(IG)":[136],"Auto-Encoder":[138],"(AE).":[139],"experimental":[141],"results":[142],"show":[143],"most":[148,200],"classical":[150],"classifiers,":[151],"Random":[153],"Forest":[154],"classifier,":[155],"shows":[156],"decline":[158,202],"accuracy":[160,205],"4.2%,":[162],"5.3%":[163],"8.8%":[165],"obtained":[172,217],"IG":[174],"AE":[176],"respectively.":[177],"To":[178],"establish":[179],"observed":[181,207],"facts":[182],"further":[184],"extensively":[185],"experimented":[186],"Decision":[188],"Tree,":[189],"Bagging,":[190],"Gradient":[191],"Boost,":[192,194],"XG":[193],"Deep":[196,210],"Neural":[197,211],"Network.":[198],"significant":[201],"(12.2%)":[203],"was":[206],"Network":[212],"classifier":[213],"IG,":[219],"i.e.,":[220],"earlier":[222],"reported":[223],"data":[233],"is":[234],"exaggerated,":[235],"consequently":[237],"it":[238],"lead":[240],"wrong":[243],"direction":[244],"field":[247],"research.":[249]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3217279074","counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2024-12-11T21:59:13.094742","created_date":"2021-12-06"}