Malicious code detection based on many‐objective transfer model
With the rapid growth of malicious codes, personal privacy, and Internet security are seriously threatened. Existing transfer learning‐based malicious code detection improves detection accuracy by transferring pre‐trained neural networks. However, it cannot efficiently tune the structure and paramet...
Gespeichert in:
Veröffentlicht in: | Concurrency and computation 2023-10, Vol.35 (22) |
---|---|
Hauptverfasser: | , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | 22 |
container_start_page | |
container_title | Concurrency and computation |
container_volume | 35 |
creator | Zhang, Binquan Wu, Di Lan, Zhuoxuan Cui, Zhihua Xie, Liping |
description | With the rapid growth of malicious codes, personal privacy, and Internet security are seriously threatened. Existing transfer learning‐based malicious code detection improves detection accuracy by transferring pre‐trained neural networks. However, it cannot efficiently tune the structure and parameters of the neural networks. Here, we first propose a novel many‐objective transfer model. It mainly focuses on the detection accuracy and the total number of parameters of the neural network model. The optimal structure and parameters are captured from the pre‐trained neural network by many‐objective optimization algorithm. Second, the partitioned crossover‐mutation vector angle‐based evolutionary algorithm for unconstrained many‐objective optimization is proposed to solve the model. The algorithm performs crossover mutation operations in different ways on different regions of the candidate solution to improve population diversity. The simulation results show that the model can reduce the pre‐trained neural network structure by 49% while maintaining the accuracy in malicious code detection. |
doi_str_mv | 10.1002/cpe.7728 |
format | Article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2861559270</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2861559270</sourcerecordid><originalsourceid>FETCH-LOGICAL-c216t-183e3237d226c0f912a14aa2b8a373f5b2fb3e161aa7c1e6fdcfcf0d6185abcb3</originalsourceid><addsrcrecordid>eNo9kM1Kw0AQxxdRsFbBRwh48ZK6M9ts0mMpfkHFi56X2c0sJKTZupsKvfkIPqNPYkrF0_xh_h_wE-Ia5AykxDu35VlZYnUiJlAozKVW89N_jfpcXKTUSgkgFUzE8oW6xjVhlzIXas5qHtgNTegzS4nrbBQb6vc_X9_BtofPJ2dDpD55jtlmTHSX4sxTl_jq707F-8P92-opX78-Pq-W69wh6CGHSrFCVdaI2km_ACSYE6GtSJXKFxa9VQwaiEoHrH3tvPOy1lAVZJ1VU3Fz7N3G8LHjNJg27GI_ThqsNBTFAks5um6PLhdDSpG92cZmQ3FvQJoDIDMCMgdA6he7V1ms</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2861559270</pqid></control><display><type>article</type><title>Malicious code detection based on many‐objective transfer model</title><source>Access via Wiley Online Library</source><creator>Zhang, Binquan ; Wu, Di ; Lan, Zhuoxuan ; Cui, Zhihua ; Xie, Liping</creator><creatorcontrib>Zhang, Binquan ; Wu, Di ; Lan, Zhuoxuan ; Cui, Zhihua ; Xie, Liping</creatorcontrib><description>With the rapid growth of malicious codes, personal privacy, and Internet security are seriously threatened. Existing transfer learning‐based malicious code detection improves detection accuracy by transferring pre‐trained neural networks. However, it cannot efficiently tune the structure and parameters of the neural networks. Here, we first propose a novel many‐objective transfer model. It mainly focuses on the detection accuracy and the total number of parameters of the neural network model. The optimal structure and parameters are captured from the pre‐trained neural network by many‐objective optimization algorithm. Second, the partitioned crossover‐mutation vector angle‐based evolutionary algorithm for unconstrained many‐objective optimization is proposed to solve the model. The algorithm performs crossover mutation operations in different ways on different regions of the candidate solution to improve population diversity. The simulation results show that the model can reduce the pre‐trained neural network structure by 49% while maintaining the accuracy in malicious code detection.</description><identifier>ISSN: 1532-0626</identifier><identifier>EISSN: 1532-0634</identifier><identifier>DOI: 10.1002/cpe.7728</identifier><language>eng</language><publisher>Hoboken: Wiley Subscription Services, Inc</publisher><subject>Accuracy ; Crossovers ; Evolutionary algorithms ; Malware ; Mathematical models ; Mutation ; Neural networks ; Optimization ; Parameters</subject><ispartof>Concurrency and computation, 2023-10, Vol.35 (22)</ispartof><rights>2023 John Wiley & Sons, Ltd.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c216t-183e3237d226c0f912a14aa2b8a373f5b2fb3e161aa7c1e6fdcfcf0d6185abcb3</cites><orcidid>0000-0002-6468-9842</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>Zhang, Binquan</creatorcontrib><creatorcontrib>Wu, Di</creatorcontrib><creatorcontrib>Lan, Zhuoxuan</creatorcontrib><creatorcontrib>Cui, Zhihua</creatorcontrib><creatorcontrib>Xie, Liping</creatorcontrib><title>Malicious code detection based on many‐objective transfer model</title><title>Concurrency and computation</title><description>With the rapid growth of malicious codes, personal privacy, and Internet security are seriously threatened. Existing transfer learning‐based malicious code detection improves detection accuracy by transferring pre‐trained neural networks. However, it cannot efficiently tune the structure and parameters of the neural networks. Here, we first propose a novel many‐objective transfer model. It mainly focuses on the detection accuracy and the total number of parameters of the neural network model. The optimal structure and parameters are captured from the pre‐trained neural network by many‐objective optimization algorithm. Second, the partitioned crossover‐mutation vector angle‐based evolutionary algorithm for unconstrained many‐objective optimization is proposed to solve the model. The algorithm performs crossover mutation operations in different ways on different regions of the candidate solution to improve population diversity. The simulation results show that the model can reduce the pre‐trained neural network structure by 49% while maintaining the accuracy in malicious code detection.</description><subject>Accuracy</subject><subject>Crossovers</subject><subject>Evolutionary algorithms</subject><subject>Malware</subject><subject>Mathematical models</subject><subject>Mutation</subject><subject>Neural networks</subject><subject>Optimization</subject><subject>Parameters</subject><issn>1532-0626</issn><issn>1532-0634</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><recordid>eNo9kM1Kw0AQxxdRsFbBRwh48ZK6M9ts0mMpfkHFi56X2c0sJKTZupsKvfkIPqNPYkrF0_xh_h_wE-Ia5AykxDu35VlZYnUiJlAozKVW89N_jfpcXKTUSgkgFUzE8oW6xjVhlzIXas5qHtgNTegzS4nrbBQb6vc_X9_BtofPJ2dDpD55jtlmTHSX4sxTl_jq707F-8P92-opX78-Pq-W69wh6CGHSrFCVdaI2km_ACSYE6GtSJXKFxa9VQwaiEoHrH3tvPOy1lAVZJ1VU3Fz7N3G8LHjNJg27GI_ThqsNBTFAks5um6PLhdDSpG92cZmQ3FvQJoDIDMCMgdA6he7V1ms</recordid><startdate>20231010</startdate><enddate>20231010</enddate><creator>Zhang, Binquan</creator><creator>Wu, Di</creator><creator>Lan, Zhuoxuan</creator><creator>Cui, Zhihua</creator><creator>Xie, Liping</creator><general>Wiley Subscription Services, Inc</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0002-6468-9842</orcidid></search><sort><creationdate>20231010</creationdate><title>Malicious code detection based on many‐objective transfer model</title><author>Zhang, Binquan ; Wu, Di ; Lan, Zhuoxuan ; Cui, Zhihua ; Xie, Liping</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c216t-183e3237d226c0f912a14aa2b8a373f5b2fb3e161aa7c1e6fdcfcf0d6185abcb3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Accuracy</topic><topic>Crossovers</topic><topic>Evolutionary algorithms</topic><topic>Malware</topic><topic>Mathematical models</topic><topic>Mutation</topic><topic>Neural networks</topic><topic>Optimization</topic><topic>Parameters</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zhang, Binquan</creatorcontrib><creatorcontrib>Wu, Di</creatorcontrib><creatorcontrib>Lan, Zhuoxuan</creatorcontrib><creatorcontrib>Cui, Zhihua</creatorcontrib><creatorcontrib>Xie, Liping</creatorcontrib><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>Concurrency and computation</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zhang, Binquan</au><au>Wu, Di</au><au>Lan, Zhuoxuan</au><au>Cui, Zhihua</au><au>Xie, Liping</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Malicious code detection based on many‐objective transfer model</atitle><jtitle>Concurrency and computation</jtitle><date>2023-10-10</date><risdate>2023</risdate><volume>35</volume><issue>22</issue><issn>1532-0626</issn><eissn>1532-0634</eissn><abstract>With the rapid growth of malicious codes, personal privacy, and Internet security are seriously threatened. Existing transfer learning‐based malicious code detection improves detection accuracy by transferring pre‐trained neural networks. However, it cannot efficiently tune the structure and parameters of the neural networks. Here, we first propose a novel many‐objective transfer model. It mainly focuses on the detection accuracy and the total number of parameters of the neural network model. The optimal structure and parameters are captured from the pre‐trained neural network by many‐objective optimization algorithm. Second, the partitioned crossover‐mutation vector angle‐based evolutionary algorithm for unconstrained many‐objective optimization is proposed to solve the model. The algorithm performs crossover mutation operations in different ways on different regions of the candidate solution to improve population diversity. The simulation results show that the model can reduce the pre‐trained neural network structure by 49% while maintaining the accuracy in malicious code detection.</abstract><cop>Hoboken</cop><pub>Wiley Subscription Services, Inc</pub><doi>10.1002/cpe.7728</doi><orcidid>https://orcid.org/0000-0002-6468-9842</orcidid></addata></record> |
fulltext | fulltext |
identifier | ISSN: 1532-0626 |
ispartof | Concurrency and computation, 2023-10, Vol.35 (22) |
issn | 1532-0626 1532-0634 |
language | eng |
recordid | cdi_proquest_journals_2861559270 |
source | Access via Wiley Online Library |
subjects | Accuracy Crossovers Evolutionary algorithms Malware Mathematical models Mutation Neural networks Optimization Parameters |
title | Malicious code detection based on many‐objective transfer model |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T00%3A33%3A22IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Malicious%20code%20detection%20based%20on%20many%E2%80%90objective%20transfer%20model&rft.jtitle=Concurrency%20and%20computation&rft.au=Zhang,%20Binquan&rft.date=2023-10-10&rft.volume=35&rft.issue=22&rft.issn=1532-0626&rft.eissn=1532-0634&rft_id=info:doi/10.1002/cpe.7728&rft_dat=%3Cproquest_cross%3E2861559270%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2861559270&rft_id=info:pmid/&rfr_iscdi=true |