東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

Automated Machine Learning for Malware Detection with Deep Learning.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Automated Machine Learning for Malware Detection with Deep Learning./
作者:	Brown, Austin.
面頁冊數:	1 online resource (72 pages)
附註:	Source: Masters Abstracts International, Volume: 84-03.
Contained By:	Masters Abstracts International84-03.
標題:	Computer science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29258983click for full text (PQDT)
ISBN:	9798841746997

Automated Machine Learning for Malware Detection with Deep Learning.
Brown, Austin.

Automated Machine Learning for Malware Detection with Deep Learning. - 1 online resource (72 pages)

Source: Masters Abstracts International, Volume: 84-03.

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

Includes bibliographical references

Deep learning (DL) has proven to be very effective in detecting sophisticated malware that is constantly evolving. Even though deep learning has alleviated the feature engineering problem, finding the most optimal DL model, in terms of neural architecture search (NAS) and the model's optimal set of hyper-parameters, remains a challenge that requires domain expertise. In addition, many of the proposed state-of-the-art models are very complex and may not be the best fit for different datasets. A promising approach, known as Automated Machine Learning (AutoML), can reduce the domain expertise required to implement a custom DL model. AutoML reduces the amount of human trial-and-error involved in designing DL models, and in more recent implementations can find new model architectures with relatively low computational overhead.Research on the feasibility of using AutoML for malware detection is very limited.As such, first, this thesis provides a comprehensive analysis and insights on using AutoML for static malware detection. Our analysis is performed on two widely used malware datasets: SOREL-20M to demonstrate efficacy on large datasets; and EMBER-2018, a smaller dataset specifically curated to hinder the performance of machine learning models. In addition, we show the effects of tuning the NAS process parameters on finding a more optimal malware detection model on these static analysis datasets.We also show that AutoML is performant in online detection scenarios using Convolutional Neural Networks (CNNs) to detect malware execution. We compare an AutoML technique to six existing state-of-the-art CNNs using a newly generated online malware dataset with and without other applications running in the background during malware execution. We show that the AutoML technique is more performant than the state-of-the-art CNNs with little overhead in finding the architecture.Our experimental results show that the performance of AutoML based malware detection models are on par or better than state-of-the-art models or hand-designed models designed presented in other works.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2023

Mode of access: World Wide Web

ISBN: 9798841746997Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Automated machine learningIndex Terms--Genre/Form:

542853
Electronic books.

Automated Machine Learning for Malware Detection with Deep Learning.
LDR:03483nmm a2200421K 4500 001 2356766
005 20230619080108.5
006 m o d
007 cr mn ---uuuuu
008 241011s2022 xx obm 000 0 eng d
020 $a 9798841746997
035 $a (MiAaPQ)AAI29258983
035 $a AAI29258983
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Brown, Austin. $3 3688842
245 1 0 $a Automated Machine Learning for Malware Detection with Deep Learning.
264 0 $c 2022
300 $a 1 online resource (72 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: 84-03.
500 $a Advisor: Gupta, Maanak.
502 $a Thesis (M.S.)--Tennessee Technological University, 2022.
504 $a Includes bibliographical references
520 $a Deep learning (DL) has proven to be very effective in detecting sophisticated malware that is constantly evolving. Even though deep learning has alleviated the feature engineering problem, finding the most optimal DL model, in terms of neural architecture search (NAS) and the model's optimal set of hyper-parameters, remains a challenge that requires domain expertise. In addition, many of the proposed state-of-the-art models are very complex and may not be the best fit for different datasets. A promising approach, known as Automated Machine Learning (AutoML), can reduce the domain expertise required to implement a custom DL model. AutoML reduces the amount of human trial-and-error involved in designing DL models, and in more recent implementations can find new model architectures with relatively low computational overhead.Research on the feasibility of using AutoML for malware detection is very limited.As such, first, this thesis provides a comprehensive analysis and insights on using AutoML for static malware detection. Our analysis is performed on two widely used malware datasets: SOREL-20M to demonstrate efficacy on large datasets; and EMBER-2018, a smaller dataset specifically curated to hinder the performance of machine learning models. In addition, we show the effects of tuning the NAS process parameters on finding a more optimal malware detection model on these static analysis datasets.We also show that AutoML is performant in online detection scenarios using Convolutional Neural Networks (CNNs) to detect malware execution. We compare an AutoML technique to six existing state-of-the-art CNNs using a newly generated online malware dataset with and without other applications running in the background during malware execution. We show that the AutoML technique is more performant than the state-of-the-art CNNs with little overhead in finding the architecture.Our experimental results show that the performance of AutoML based malware detection models are on par or better than state-of-the-art models or hand-designed models designed presented in other works.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 523869
650 4 $a Computer engineering. $3 621879
650 4 $a Information technology. $3 532993
653 $a Automated machine learning
653 $a AutoML
653 $a Cyber security
653 $a Deep learning
653 $a Machine learning
653 $a Malware
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0984
690 $a 0489
690 $a 0464
690 $a 0800
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a Tennessee Technological University. $b Computer Science. $3 1681403
773 0 $t Masters Abstracts International $g 84-03.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29258983 $z click for full text (PQDT)