{"id":"https://openalex.org/W4311165833","doi":"https://doi.org/10.1145/3564625.3564661","title":"Make Data Reliable: An Explanation-powered Cleaning on Malware Dataset Against Backdoor Poisoning Attacks","display_name":"Make Data Reliable: An Explanation-powered Cleaning on Malware Dataset Against Backdoor Poisoning Attacks","publication_year":2022,"publication_date":"2022-12-03","ids":{"openalex":"https://openalex.org/W4311165833","doi":"https://doi.org/10.1145/3564625.3564661"},"language":"en","primary_location":{"id":"doi:10.1145/3564625.3564661","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3564625.3564661","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3564625.3564661","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th Annual Computer Security Applications Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3564625.3564661","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014763916","display_name":"Xutong Wang","orcid":"https://orcid.org/0000-0001-7712-7884"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xutong Wang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, China and School of Cyber Security, University of Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0001-7712-7884","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, China and School of Cyber Security, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086981720","display_name":"Chaoge Liu","orcid":"https://orcid.org/0000-0002-8023-3941"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaoge Liu","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, China and School of Cyber Security, University of Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0002-8023-3941","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, China and School of Cyber Security, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086743317","display_name":"Xiaohui Hu","orcid":"https://orcid.org/0000-0002-1485-2832"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohui Hu","raw_affiliation_strings":["School of Computer Science, Beijing University of Posts and Telecommunications, China"],"raw_orcid":"https://orcid.org/0000-0002-1485-2832","affiliations":[{"raw_affiliation_string":"School of Computer Science, Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693759","display_name":"Zhi Wang","orcid":"https://orcid.org/0000-0003-4711-4251"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Wang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, China and School of Cyber Security, University of Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0003-4711-4251","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, China and School of Cyber Security, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101489990","display_name":"Jie Yin","orcid":"https://orcid.org/0000-0002-6025-1915"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Yin","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100294045","display_name":"Xiang Cui","orcid":"https://orcid.org/0009-0002-2215-5620"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Cui","raw_affiliation_strings":["Zhongguancun Laboratory, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhongguancun Laboratory, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"267","last_page":"278"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9998000264167786,"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":0.9998000264167786,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9995999932289124,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9980999827384949,"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/backdoor","display_name":"Backdoor","score":0.8665124177932739},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8243155479431152},{"id":"https://openalex.org/keywords/malware","display_name":"Malware","score":0.7933096289634705},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5629748702049255},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5272811055183411},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4987490177154541},{"id":"https://openalex.org/keywords/watermark","display_name":"Watermark","score":0.4714789390563965},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.459117591381073},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4140443801879883},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.4074793756008148},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.2652079463005066}],"concepts":[{"id":"https://openalex.org/C2781045450","wikidata":"https://www.wikidata.org/wiki/Q254569","display_name":"Backdoor","level":2,"score":0.8665124177932739},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8243155479431152},{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.7933096289634705},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5629748702049255},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5272811055183411},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4987490177154541},{"id":"https://openalex.org/C164112704","wikidata":"https://www.wikidata.org/wiki/Q7974348","display_name":"Watermark","level":3,"score":0.4714789390563965},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.459117591381073},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4140443801879883},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.4074793756008148},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.2652079463005066},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3564625.3564661","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3564625.3564661","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3564625.3564661","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th Annual Computer Security Applications Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3564625.3564661","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3564625.3564661","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3564625.3564661","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th Annual Computer Security Applications Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G289734625","display_name":null,"funder_award_id":"No.61902396","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3260406069","display_name":null,"funder_award_id":"61902396","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3390532264","display_name":null,"funder_award_id":"XDC02040100","funder_id":"https://openalex.org/F4320321133","funder_display_name":"Chinese Academy of Sciences"},{"id":"https://openalex.org/G529307786","display_name":null,"funder_award_id":"2019163","funder_id":"https://openalex.org/F4320322847","funder_display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences"},{"id":"https://openalex.org/G8058437614","display_name":null,"funder_award_id":"XDC02040100","funder_id":"https://openalex.org/F4320322847","funder_display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences"},{"id":"https://openalex.org/G8701658582","display_name":null,"funder_award_id":"No.2019163","funder_id":"https://openalex.org/F4320322847","funder_display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"},{"id":"https://openalex.org/F4320335892","display_name":"Youth Innovation Promotion Association","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4311165833.pdf","grobid_xml":"https://content.openalex.org/works/W4311165833.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1488996941","https://openalex.org/W1552056088","https://openalex.org/W2046185165","https://openalex.org/W2082190528","https://openalex.org/W2103154003","https://openalex.org/W2126047957","https://openalex.org/W2131681506","https://openalex.org/W2158703410","https://openalex.org/W2791218785","https://openalex.org/W2798248638","https://openalex.org/W2807363941","https://openalex.org/W2900587877","https://openalex.org/W2922344003","https://openalex.org/W2934843808","https://openalex.org/W2963165448","https://openalex.org/W2964136807","https://openalex.org/W2985913519","https://openalex.org/W2990270730","https://openalex.org/W3099768174","https://openalex.org/W3106196258","https://openalex.org/W3163186834","https://openalex.org/W3204619801","https://openalex.org/W3215076255","https://openalex.org/W4225750584","https://openalex.org/W4230172274"],"related_works":["https://openalex.org/W4320031223","https://openalex.org/W4200629851","https://openalex.org/W4281902577","https://openalex.org/W4309417370","https://openalex.org/W4292107232","https://openalex.org/W3009072493","https://openalex.org/W4386080799","https://openalex.org/W3140988292","https://openalex.org/W4317672133","https://openalex.org/W4386185023"],"abstract_inverted_index":{"Machine":[0],"learning":[1],"(ML)":[2],"based":[3,146],"Malware":[4],"classification":[5,20],"provides":[6],"excellent":[7],"performance":[8],"and":[9,82,113,131,152,198],"has":[10],"been":[11],"deployed":[12],"in":[13],"various":[14],"real-world":[15,36],"applications.":[16],"Training":[17],"for":[18,39,86,195],"malware":[19,45,88],"often":[21],"relies":[22],"on":[23,43,147,169,242],"crowdsourced":[24],"threat":[25,37,79,93],"feeds,":[26],"which":[27,109],"exposes":[28],"a":[29,35,44,62,65,111,128,162,226,235],"natural":[30],"attack":[31,179,199],"injection":[32],"point.":[33],"Considering":[34],"model":[38,130],"backdoor":[40,95],"poisoning":[41],"attacks":[42],"dataset,":[46],"because":[47],"attackers":[48],"are":[49],"generally":[50],"considered":[51],"to":[52,116,138,160,214,224],"have":[53],"no":[54],"control":[55],"over":[56],"the":[57,84,92,118,148,157,185,216],"sample-labeling":[58],"process,":[59],"they":[60],"conduct":[61,166],"clean-label":[63],"attack,":[64],"more":[66],"realistic":[67],"scenario,":[68],"by":[69,122],"generating":[70],"backdoored":[71,124,188],"benign":[72],"binaries":[73],"that":[74,173,184,238],"will":[75],"be":[76],"disseminated":[77],"through":[78],"intelligence":[80],"platforms":[81],"poison":[83],"datasets":[85,121,172,197],"downstream":[87],"classifiers.":[89],"To":[90],"avoid":[91],"of":[94,120,209,218],"poisoned":[96,176],"datasets,":[97],"we":[98,220],"propose":[99],"an":[100,203],"explanation-powered":[101],"defense":[102],"methodology":[103,237],"called":[104],"make":[105],"data":[106],"reliable":[107,163],"(MDR),":[108],"is":[110,234],"general":[112,236],"effective":[114],"mitigation":[115],"ensure":[117],"reliability":[119],"removing":[123],"samples.":[125],"We":[126,165],"use":[127,221],"surrogate":[129],"explanation":[132],"tool":[133],"Shapley":[134],"Additive":[135],"exPlanations":[136],"(SHAP)":[137],"filter":[139],"suspicious":[140,150],"samples,":[141,151],"then":[142],"perform":[143,225],"watermark":[144,159],"identification":[145],"filtered":[149],"finally":[153],"remove":[154],"samples":[155,189],"with":[156],"identified":[158],"construct":[161],"dataset.":[164],"extensive":[167],"experiments":[168],"two":[170],"typical":[171],"were":[174],"manually":[175],"using":[177],"different":[178,196,222],"strategies.":[180],"Experimental":[181],"results":[182,230],"show":[183,231],"MDR":[186,233],"achieves":[187],"removal":[190],"rate":[191,208],"greater":[192],"than":[193,211],"99.0%":[194],"conditions,":[200],"while":[201],"maintaining":[202],"extremely":[204],"low":[205],"false":[206],"positive":[207],"less":[210],"0.1%.":[212],"Furthermore,":[213],"confirm":[215],"generality":[217],"MDR,":[219],"models":[223],"model-agnostic":[227],"evaluation.":[228],"The":[229],"that,":[232],"does":[239],"not":[240],"rely":[241],"any":[243],"specific":[244],"model.":[245]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}