{"id":"https://openalex.org/W4385438587","doi":"https://doi.org/10.1145/3609510.3609818","title":"Family Classification based on Tree Representations for Malware","display_name":"Family Classification based on Tree Representations for Malware","publication_year":2023,"publication_date":"2023-07-31","ids":{"openalex":"https://openalex.org/W4385438587","doi":"https://doi.org/10.1145/3609510.3609818"},"language":"en","primary_location":{"id":"doi:10.1145/3609510.3609818","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3609510.3609818","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM SIGOPS Asia-Pacific Workshop on Systems","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/A5101440477","display_name":"Yang Xu","orcid":"https://orcid.org/0000-0002-9401-9313"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yang Xu","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111477510","display_name":"Zhengli Chen","orcid":"https://orcid.org/0009-0005-5827-536X"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuotai Chen","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101440477"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":0.5943,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.64395536,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"65","last_page":"71"},"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":0.9990000128746033,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9843000173568726,"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/malware","display_name":"Malware","score":0.9080321788787842},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.781110405921936},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.6773049831390381},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5522989630699158},{"id":"https://openalex.org/keywords/malware-analysis","display_name":"Malware analysis","score":0.5520235300064087},{"id":"https://openalex.org/keywords/system-call","display_name":"System call","score":0.5118710398674011},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.4696245491504669},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.459644079208374},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44554391503334045},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.43559810519218445},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.43209895491600037},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.4137667417526245},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4117831587791443},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.40366166830062866},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11512342095375061},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.10690498352050781},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08438840508460999}],"concepts":[{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.9080321788787842},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.781110405921936},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.6773049831390381},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5522989630699158},{"id":"https://openalex.org/C2779395397","wikidata":"https://www.wikidata.org/wiki/Q15731404","display_name":"Malware analysis","level":3,"score":0.5520235300064087},{"id":"https://openalex.org/C2778579508","wikidata":"https://www.wikidata.org/wiki/Q722192","display_name":"System call","level":2,"score":0.5118710398674011},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.4696245491504669},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.459644079208374},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44554391503334045},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.43559810519218445},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.43209895491600037},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.4137667417526245},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4117831587791443},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.40366166830062866},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11512342095375061},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.10690498352050781},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08438840508460999},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3609510.3609818","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3609510.3609818","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM SIGOPS Asia-Pacific Workshop on Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G988927737","display_name":null,"funder_award_id":"2020A1515010696","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W793339159","https://openalex.org/W1566259290","https://openalex.org/W1573526548","https://openalex.org/W1970635365","https://openalex.org/W2021436318","https://openalex.org/W2032338144","https://openalex.org/W2044751544","https://openalex.org/W2057787526","https://openalex.org/W2126401948","https://openalex.org/W2301473744","https://openalex.org/W2340189285","https://openalex.org/W2553476679","https://openalex.org/W2600031682","https://openalex.org/W2625696220","https://openalex.org/W2754462941","https://openalex.org/W2780450026","https://openalex.org/W2911286998","https://openalex.org/W2914516771","https://openalex.org/W2946655834","https://openalex.org/W2959221393","https://openalex.org/W2972552958","https://openalex.org/W4243932450"],"related_works":["https://openalex.org/W2469507153","https://openalex.org/W2008790809","https://openalex.org/W1998188341","https://openalex.org/W2400599487","https://openalex.org/W2469346691","https://openalex.org/W3211525895","https://openalex.org/W2765174411","https://openalex.org/W2965893286","https://openalex.org/W2991580804","https://openalex.org/W2810666735"],"abstract_inverted_index":{"Malware":[0],"classification":[1,10,63,154,186],"is":[2,13,119,140,191],"helpful":[3],"for":[4],"malware":[5,12,25,49,61,68,139,160,177,181],"detection":[6],"and":[7,148],"analysis.":[8],"Family":[9],"of":[11,99,114,131,137,159,188,196],"a":[14,59,70,97,169],"multi-classification":[15],"task.":[16],"Many":[17],"studies":[18],"have":[19],"exploited":[20],"API":[21,28,41,74,88,202],"call":[22,29,75,203],"sequences":[23,30],"as":[24,69,103,111],"features.":[26],"However,":[27],"do":[31],"not":[32],"explicitly":[33],"express":[34],"the":[35,83,87,92,108,123,128,134,144,150,156,185,197],"information":[36],"about":[37],"control":[38,84],"structures":[39],"between":[40,86,146],"calls,":[42],"which":[43,81],"may":[44],"be":[45],"useful":[46],"to":[47,121,167],"represent":[48],"behavior":[50,109,112,125,129],"features":[51,113,126,130],"more":[52],"accurately.":[53],"In":[54],"this":[55],"paper,":[56],"we":[57,95],"propose":[58],"novel":[60],"familial":[62],"method.":[64],"We":[65],"model":[66],"each":[67,138],"Behavioral":[71],"Tree":[72],"from":[73,78,107,127,179],"sequence":[76],"obtained":[77],"dynamic":[79],"analysis,":[80],"describes":[82],"structure":[85],"calls.":[89],"To":[90],"reduce":[91],"computational":[93],"complexity,":[94],"capture":[96],"set":[98],"binary":[100],"relations,":[101],"called":[102],"Heighted":[104],"Behavior":[105],"Relations,":[106],"tree":[110],"malware.":[115,132],"The":[116,171],"TF-IDF":[117],"technology":[118],"used":[120],"calculate":[122],"family":[124,153],"Then":[133],"similarity":[135,145,157],"vector":[136],"constructed":[141],"based":[142,200],"on":[143,173,201],"it":[147],"all":[149],"families.":[151],"For":[152],"purpose,":[155],"vectors":[158],"are":[161],"fed":[162],"into":[163],"Naive":[164],"Bayes":[165],"algorithm":[166],"train":[168],"classifier.":[170],"experiments":[172],"dataset":[174],"with":[175],"10620":[176],"samples":[178],"43":[180],"families":[182],"show":[183],"that":[184,195],"accuracy":[187],"our":[189],"approach":[190],"10%":[192],"higher":[193],"than":[194],"classical":[198],"methods":[199],"sequences.":[204]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}