國立虎尾科技大學 |

Analyzing and Explaining Machine Learning Based Online Malware Detection in Cloud.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Analyzing and Explaining Machine Learning Based Online Malware Detection in Cloud./
作者:	Kimmell, Jeffrey Calen.
面頁冊數:	1 online resource (82 pages)
附註:	Source: Masters Abstracts International, Volume: 83-11.
Contained By:	Masters Abstracts International83-11.
標題:	Computer science. -
電子資源:	click for full text (PQDT)
ISBN:	9798438791386

Analyzing and Explaining Machine Learning Based Online Malware Detection in Cloud.
Kimmell, Jeffrey Calen.

Analyzing and Explaining Machine Learning Based Online Malware Detection in Cloud. - 1 online resource (82 pages)

Source: Masters Abstracts International, Volume: 83-11.

Thesis (M.S.)--Tennessee Technological University, 2022.

Includes bibliographical references

The introduction of cloud environments for work flows and other uses has led to a dramatic shift for private firms and government entities alike. These cloud environments are constructed and offered by cloud service providers (CSP). Key CSPs such as Google, Microsoft, and Amazon offer products and services that provide firms with scalable infrastructure options without firms having to invest in hardware; this is known as infrastructure as a service (IaaS). This infrastructure allows for a central point for collaborators to work and access resources. This nature of IaaS makes these cloud environments very attractive to attackers. Securing these systems has become a top priority for these CSPs and researchers as compromised cloud environments can have much more drastic impacts as opposed to a single compromised machine. Malware is a common way these attackers gain access to these systems. That is why it is of the utmost importance to create sophisticated malware detection methods that can sufficiently protect these systems. This work provides a cloud specific online malware detection method and compares the effectiveness of Convolutional Neural Networks (CNN), Support Vector Classifier (SCV), Random Forest Classifier (RFC), K-Nearest Neighbor (KNN), Gradient Boosted Classifier (GBC), Gaussian Naive Bayes (GNB), and two types of Recurrent Neural Networks (RNN), Long Short Term Memory (LSTM), and Bidirectional (BIDI).We also deploy a feed-forward neural network and then use Shapley Additive Explanations (SHAP) to explain the decisions that the model produces. Our models are trained validated and tested on a dataset that contains 40,680 data points that are comprised of process sytstem features that represents the behavior of the virtual machine (VM). This data was collected by running malware openly in a cloud environment to ensure the behavior of the malware and VMs is as realistic as possible.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798438791386Subjects--Topical Terms:

573171
Computer science.
Subjects--Index Terms:

Machine learningIndex Terms--Genre/Form:

554714
Electronic books.

Analyzing and Explaining Machine Learning Based Online Malware Detection in Cloud.
LDR:03228ntm a22003617 4500 001 1147088
005 20240909062211.5
006 m o d
007 cr bn ---uuuuu
008 250605s2022 xx obm 000 0 eng d
020 $a 9798438791386
035 $a (MiAaPQ)AAI29069308
035 $a AAI29069308
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Kimmell, Jeffrey Calen. $3 1472714
245 1 0 $a Analyzing and Explaining Machine Learning Based Online Malware Detection in Cloud.
264 0 $c 2022
300 $a 1 online resource (82 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 83-11.
500 $a Advisor: Gupta, Maanak.
502 $a Thesis (M.S.)--Tennessee Technological University, 2022.
504 $a Includes bibliographical references
520 $a The introduction of cloud environments for work flows and other uses has led to a dramatic shift for private firms and government entities alike. These cloud environments are constructed and offered by cloud service providers (CSP). Key CSPs such as Google, Microsoft, and Amazon offer products and services that provide firms with scalable infrastructure options without firms having to invest in hardware; this is known as infrastructure as a service (IaaS). This infrastructure allows for a central point for collaborators to work and access resources. This nature of IaaS makes these cloud environments very attractive to attackers. Securing these systems has become a top priority for these CSPs and researchers as compromised cloud environments can have much more drastic impacts as opposed to a single compromised machine. Malware is a common way these attackers gain access to these systems. That is why it is of the utmost importance to create sophisticated malware detection methods that can sufficiently protect these systems. This work provides a cloud specific online malware detection method and compares the effectiveness of Convolutional Neural Networks (CNN), Support Vector Classifier (SCV), Random Forest Classifier (RFC), K-Nearest Neighbor (KNN), Gradient Boosted Classifier (GBC), Gaussian Naive Bayes (GNB), and two types of Recurrent Neural Networks (RNN), Long Short Term Memory (LSTM), and Bidirectional (BIDI).We also deploy a feed-forward neural network and then use Shapley Additive Explanations (SHAP) to explain the decisions that the model produces. Our models are trained validated and tested on a dataset that contains 40,680 data points that are comprised of process sytstem features that represents the behavior of the virtual machine (VM). This data was collected by running malware openly in a cloud environment to ensure the behavior of the malware and VMs is as realistic as possible.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
653 $a Machine learning
653 $a Online malware detection
653 $a Cloud service providers
653 $a Virtual machines
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Tennessee Technological University. $b Computer Science. $3 1413540
773 0 $t Masters Abstracts International $g 83-11.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29069308 $z click for full text (PQDT)