Please use this identifier to cite or link to this item:
http://hdl.handle.net/10603/513054
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.coverage.spatial | ||
dc.date.accessioned | 2023-09-21T07:07:45Z | - |
dc.date.available | 2023-09-21T07:07:45Z | - |
dc.identifier.uri | http://hdl.handle.net/10603/513054 | - |
dc.description.abstract | Cyberspace is fraught with dangers, one of which is the distributed denial of service newlineattack (DDoS). This type of attack is particularly concerning as it can disrupt vital newlineservices, prevent authorized users from accessing them, and result in financial losses. newlineThis research is divided into three phases. The first phase presents DDoS attack detection newlineusing three machine learning algorithms, namely; support vector machine (SVM), knearest neighbors (KNN), and random forest (RF) classifier. The outcome of developed newlinealgorithms is recorded on the basis of evaluations parameters; accuracy, precision, newlinesensitivity, and F1-score. The aim of second phase of the research is to present an newlineoptimized AdaBoost classifier that has been fine-tuned using the HFPSO algorithm. The newlinedata is pre-processed to ensure that it conforms to standard features by normalizing it. newlineAdditionally, cross-correlation techniques are used to select features in order to eliminate newlineredundancy. Finally, the constructed signals are used to train and test an HFPSOoptimized AdaBoost classifier. The result indicates the possibility of anticipating the newlineattacks is fairly accurate. The system accuracy is 99.97%. The final phase of research newlinework proposes a novel approach for detecting DDoS attacks using a spiking neural newlinenetwork (SNN) with a distance-based rate coding mechanism and optimizing the SNN newlineusing a genetic algorithm (GA). There is another approach, Fuzzy Fused CNN and SNN newlineclassifiers is also presented. The proposed GA-SNN approach achieved a remarkable newlineaccuracy rate of 99.98% in detecting DDoS attacks, outperforming existing state-of-theart methods. The GA optimization approach helps to overcome the challenges of setting newlinethe initial weights and biases in the SNN, and the distance-based rate coding mechanism newlineenhances the accuracy of the SNN in detecting DDoS attacks. Additionally, the proposed newlineapproach is designed to be computationally efficient, which is essential for practical newlineimplementation in real-time systems. Overall, the proposed GA-SNN approach is a newline | |
dc.format.extent | ||
dc.language | English | |
dc.relation | ||
dc.rights | university | |
dc.title | Efficient DDoS Attack Detection Using Ensemble of Neural Network | |
dc.title.alternative | ||
dc.creator.researcher | Pawar Anuradha Bhalerao (19ENG7ECE0005) | |
dc.subject.keyword | Engineering | |
dc.subject.keyword | Engineering and Technology | |
dc.subject.keyword | Engineering Electrical and Electronic | |
dc.description.note | ||
dc.contributor.guide | Tiwari Nidhi | |
dc.publisher.place | Indore | |
dc.publisher.university | SAGE University, Indore | |
dc.publisher.institution | Faculty of Engineering and Technology | |
dc.date.registered | 2019 | |
dc.date.completed | 2023 | |
dc.date.awarded | 2023 | |
dc.format.dimensions | ||
dc.format.accompanyingmaterial | DVD | |
dc.source.university | University | |
dc.type.degree | Ph.D. | |
Appears in Departments: | Faculty of Engineering & Technology |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
01_title.pdf | Attached File | 435.03 kB | Adobe PDF | View/Open |
02_prelim pages.pdf | 2.63 MB | Adobe PDF | View/Open | |
03_abstract.pdf | 303.2 kB | Adobe PDF | View/Open | |
04_content.pdf | 724.18 kB | Adobe PDF | View/Open | |
05_chapter 1.pdf | 584.82 kB | Adobe PDF | View/Open | |
06_chapter 2.pdf | 791.41 kB | Adobe PDF | View/Open | |
07_chapter 3.pdf | 774.35 kB | Adobe PDF | View/Open | |
08_chapter 4.pdf | 1.07 MB | Adobe PDF | View/Open | |
09_chapter 5.pdf | 1.23 MB | Adobe PDF | View/Open | |
10_annexures.pdf | 3.6 MB | Adobe PDF | View/Open | |
80_recommendation.pdf | 293.46 kB | Adobe PDF | View/Open |
Items in Shodhganga are licensed under Creative Commons Licence Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).
Altmetric Badge: