Conglomerate Stratum Model for Categorization of Malware Family in Image Processing

IF 1.3 Q2 MATHEMATICS, APPLIED
Rupali Komatwar, Manesh Kokare
{"title":"Conglomerate Stratum Model for Categorization of Malware Family in Image Processing","authors":"Rupali Komatwar, Manesh Kokare","doi":"10.26599/fie.2023.9270016","DOIUrl":null,"url":null,"abstract":"In recent years, there has been an enormous increase in the volume of malware generation and the classification of malware samples plays a crucial role in building and maintaining security. Hence, there is a need to explore new approaches to overcome the limitations of malware classification such as pre-combustion, peculiarity eradication, and categorization. To overcome these issues, this paper proposes a novel Conglomerate Stratum Model (CSM), which categorizes them into groups and identifies their respective families based on their behavior. Initially, the precombustion process used Triad Seeped Technique (TST) in which the image is first regularized by applying ripples. Secondly, we introduced a Quatrain Layer Method (QLM) to upgrade the robustness of malware image features in peculiarity eradication. Then the specific output of the quatrain layer is given to Acclimatized Patronage Scheme (APS) for categorization, and this process effectively classifies the malware types with greater accuracy. The results demonstrate that our model can achieve 99.41% accuracy in classifying malware samples. Also, the values of sensitivity, precision, negative predictive, and recall are higher than 0.9 with the false-negative rate of 0.04, and the false-positive rate 0.003 proving the model to be optimistic. The experimental comparison demonstrates its superior performance concerning state-of-the-art techniques.","PeriodicalId":37623,"journal":{"name":"Fuzzy Information and Engineering","volume":"23 1","pages":"0"},"PeriodicalIF":1.3000,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Fuzzy Information and Engineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.26599/fie.2023.9270016","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MATHEMATICS, APPLIED","Score":null,"Total":0}
引用次数: 0

Abstract

In recent years, there has been an enormous increase in the volume of malware generation and the classification of malware samples plays a crucial role in building and maintaining security. Hence, there is a need to explore new approaches to overcome the limitations of malware classification such as pre-combustion, peculiarity eradication, and categorization. To overcome these issues, this paper proposes a novel Conglomerate Stratum Model (CSM), which categorizes them into groups and identifies their respective families based on their behavior. Initially, the precombustion process used Triad Seeped Technique (TST) in which the image is first regularized by applying ripples. Secondly, we introduced a Quatrain Layer Method (QLM) to upgrade the robustness of malware image features in peculiarity eradication. Then the specific output of the quatrain layer is given to Acclimatized Patronage Scheme (APS) for categorization, and this process effectively classifies the malware types with greater accuracy. The results demonstrate that our model can achieve 99.41% accuracy in classifying malware samples. Also, the values of sensitivity, precision, negative predictive, and recall are higher than 0.9 with the false-negative rate of 0.04, and the false-positive rate 0.003 proving the model to be optimistic. The experimental comparison demonstrates its superior performance concerning state-of-the-art techniques.
图像处理中恶意软件族分类的砾岩层模型
近年来,恶意软件的生成数量急剧增加,恶意软件样本的分类在构建和维护安全方面起着至关重要的作用。因此,有必要探索新的方法来克服恶意软件分类的局限性,如预燃烧、特性消除和分类。为了克服这些问题,本文提出了一种新的砾岩地层模型(CSM),该模型根据砾岩的行为将其分类并确定其所属的家族。最初,燃烧前的过程使用了三重渗透技术(TST),其中图像首先通过波纹进行正则化。其次,我们引入了四行层方法(QLM)来提高恶意软件图像特征在消除奇异性中的鲁棒性。然后将四行诗层的具体输出给accli驯化赞助方案(APS)进行分类,该过程有效地对恶意软件类型进行了分类,准确率更高。结果表明,该模型对恶意软件样本的分类准确率达到99.41%。灵敏度、精密度、阴性预测和召回率均大于0.9,假阴性率为0.04,假阳性率为0.003,证明模型是乐观的。实验对比证明了其在技术前沿的优越性能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
2.30
自引率
0.00%
发文量
13
审稿时长
40 weeks
期刊介绍: Fuzzy Information and Engineering—An International Journal wants to provide a unified communication platform for researchers in a wide area of topics from pure and applied mathematics, computer science, engineering, and other related fields. While also accepting fundamental work, the journal focuses on applications. Research papers, short communications, and reviews are welcome. Technical topics within the scope include: (1) Fuzzy Information a. Fuzzy information theory and information systems b. Fuzzy clustering and classification c. Fuzzy information processing d. Hardware and software co-design e. Fuzzy computer f. Fuzzy database and data mining g. Fuzzy image processing and pattern recognition h. Fuzzy information granulation i. Knowledge acquisition and representation in fuzzy information (2) Fuzzy Sets and Systems a. Fuzzy sets b. Fuzzy analysis c. Fuzzy topology and fuzzy mapping d. Fuzzy equation e. Fuzzy programming and optimal f. Fuzzy probability and statistic g. Fuzzy logic and algebra h. General systems i. Fuzzy socioeconomic system j. Fuzzy decision support system k. Fuzzy expert system (3) Soft Computing a. Soft computing theory and foundation b. Nerve cell algorithms c. Genetic algorithms d. Fuzzy approximation algorithms e. Computing with words and Quantum computation (4) Fuzzy Engineering a. Fuzzy control b. Fuzzy system engineering c. Fuzzy knowledge engineering d. Fuzzy management engineering e. Fuzzy design f. Fuzzy industrial engineering g. Fuzzy system modeling (5) Fuzzy Operations Research [...] (6) Artificial Intelligence [...] (7) Others [...]
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信