國立虎尾科技大學 |

Machine Learning for Malicious URL Classification : = A Temporal Analysis.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Machine Learning for Malicious URL Classification :/
Reminder of title:	A Temporal Analysis.
Author:	Wehr, Evan N.
Description:	1 online resource (168 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 85-06, Section: B.
Contained By:	Dissertations Abstracts International85-06B.
Subject:	Information science. -
Online resource:	click for full text (PQDT)
ISBN:	9798381097283

Machine Learning for Malicious URL Classification : = A Temporal Analysis.
Wehr, Evan N.

Machine Learning for Malicious URL Classification :A Temporal Analysis. - 1 online resource (168 pages)

Source: Dissertations Abstracts International, Volume: 85-06, Section: B.

Thesis (D.Engr.)--The George Washington University, 2024.

Includes bibliographical references

When Machine Learning (ML) is applied to labelled datasets, it is standard practice that 70% of the dataset is used for training models, with 30% used for testing. That approach assumes the dataset does not change over time. This praxis makes the case that URLs do change over time, meaning that ML performance should decay over time when applied to malicious URL classification. All studies found within the scope of this praxis, where ML was used to classify malicious URLs, used the traditional 70-30 split. Not knowing the consequences of drift and decay where ML is applied to malicious URL classification was identified as the primary knowledge gap of interest for this praxis. Models that are resistant to performance decay over time exhibit lasting power. To identify models with the strongest lasting power, a dataset was created to address the stated research questions and hypotheses, which relate to the idea that a temporal analysis can determine which ML algorithms struggle the least with drift and decay when used to classify malicious URLs. The new, temporally segmented dataset had 2,292,882 URLs, making the dataset of this praxis one of the largest malicious URL datasets to date. The temporal analysis did, indeed, reveal concept drift. Additionally, the analysis revealed that performance decay might exist, but the decay would be negligible. The presence of performance decay remains an open question that future research could explore. Models with the strongest lasting power identified herein included SVM-l, SVM-rbf, and LSVC, with the application of Normalization and Standardization. These findings provide essential novel insight so that security engineers can make informed decisions by selecting models with lasting power when designing security solutions for malicious URL classification.

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

Mode of access: World Wide Web

ISBN: 9798381097283Subjects--Topical Terms:

561178
Information science.
Subjects--Index Terms:

Machine Learning Index Terms--Genre/Form:

554714
Electronic books.

Machine Learning for Malicious URL Classification : = A Temporal Analysis.
LDR:03223ntm a22004097 4500 001 1143046
005 20240513061052.5
006 m o d
007 cr mn ---uuuuu
008 250605s2024 xx obm 000 0 eng d
020 $a 9798381097283
035 $a (MiAaPQ)AAI30815491
035 $a AAI30815491
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Wehr, Evan N. $3 1467613
245 1 0 $a Machine Learning for Malicious URL Classification : $b A Temporal Analysis.
264 0 $c 2024
300 $a 1 online resource (168 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: Dissertations Abstracts International, Volume: 85-06, Section: B.
500 $a Advisor: Rodriguez, Linda.
502 $a Thesis (D.Engr.)--The George Washington University, 2024.
504 $a Includes bibliographical references
520 $a When Machine Learning (ML) is applied to labelled datasets, it is standard practice that 70% of the dataset is used for training models, with 30% used for testing. That approach assumes the dataset does not change over time. This praxis makes the case that URLs do change over time, meaning that ML performance should decay over time when applied to malicious URL classification. All studies found within the scope of this praxis, where ML was used to classify malicious URLs, used the traditional 70-30 split. Not knowing the consequences of drift and decay where ML is applied to malicious URL classification was identified as the primary knowledge gap of interest for this praxis. Models that are resistant to performance decay over time exhibit lasting power. To identify models with the strongest lasting power, a dataset was created to address the stated research questions and hypotheses, which relate to the idea that a temporal analysis can determine which ML algorithms struggle the least with drift and decay when used to classify malicious URLs. The new, temporally segmented dataset had 2,292,882 URLs, making the dataset of this praxis one of the largest malicious URL datasets to date. The temporal analysis did, indeed, reveal concept drift. Additionally, the analysis revealed that performance decay might exist, but the decay would be negligible. The presence of performance decay remains an open question that future research could explore. Models with the strongest lasting power identified herein included SVM-l, SVM-rbf, and LSVC, with the application of Normalization and Standardization. These findings provide essential novel insight so that security engineers can make informed decisions by selecting models with lasting power when designing security solutions for malicious URL classification.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Information science. $3 561178
650 4 $a Computer science. $3 573171
650 4 $a Computer engineering. $3 569006
653 $a Machine Learning
653 $a Malicious URLs
653 $a Temporal analysis
653 $a Security solutions
653 $a Dataset
655 7 $a Electronic books. $2 local $3 554714
690 $a 0723
690 $a 0984
690 $a 0800
690 $a 0464
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a The George Washington University. $b Computer Science. $3 1148676
773 0 $t Dissertations Abstracts International $g 85-06B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30815491 $z click for full text (PQDT)