Performance analysis of deep learning algorithms for Intrusion Detection System(IDS) of IoT Security
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2022.
| Հիմնական հեղինակներ: | , , , , |
|---|---|
| Այլ հեղինակներ: | |
| Ձևաչափ: | Թեզիս |
| Լեզու: | en_US |
| Հրապարակվել է: |
Brac University
2022
|
| Խորագրեր: | |
| Առցանց հասանելիություն: | http://hdl.handle.net/10361/17213 |
| id |
10361-17213 |
|---|---|
| record_format |
dspace |
| institution |
Brac University |
| collection |
Institutional Repository |
| language |
en_US |
| topic |
Deep learning Intrusion Detection System IoT Security RNN GRU LSTM KDD-99 NSL-KDD LSTM GRU IDS Vanilla LSTM Bidirectional LSTM Stacked LSTM Machine learning. Intrusion detection systems (Computer security) Internet of things |
| spellingShingle |
Deep learning Intrusion Detection System IoT Security RNN GRU LSTM KDD-99 NSL-KDD LSTM GRU IDS Vanilla LSTM Bidirectional LSTM Stacked LSTM Machine learning. Intrusion detection systems (Computer security) Internet of things Fiha, Yeamin Jahan Farjana, Mithila Bin Masum, Syed Rifat Soron, Mehedi Bin Sarwar Alif, Mia Fahim Hasan Performance analysis of deep learning algorithms for Intrusion Detection System(IDS) of IoT Security |
| description |
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2022. |
| author2 |
Hossain, Muhammad Iqbal |
| author_facet |
Hossain, Muhammad Iqbal Fiha, Yeamin Jahan Farjana, Mithila Bin Masum, Syed Rifat Soron, Mehedi Bin Sarwar Alif, Mia Fahim Hasan |
| format |
Thesis |
| author |
Fiha, Yeamin Jahan Farjana, Mithila Bin Masum, Syed Rifat Soron, Mehedi Bin Sarwar Alif, Mia Fahim Hasan |
| author_sort |
Fiha, Yeamin Jahan |
| title |
Performance analysis of deep learning algorithms for Intrusion Detection System(IDS) of IoT Security |
| title_short |
Performance analysis of deep learning algorithms for Intrusion Detection System(IDS) of IoT Security |
| title_full |
Performance analysis of deep learning algorithms for Intrusion Detection System(IDS) of IoT Security |
| title_fullStr |
Performance analysis of deep learning algorithms for Intrusion Detection System(IDS) of IoT Security |
| title_full_unstemmed |
Performance analysis of deep learning algorithms for Intrusion Detection System(IDS) of IoT Security |
| title_sort |
performance analysis of deep learning algorithms for intrusion detection system(ids) of iot security |
| publisher |
Brac University |
| publishDate |
2022 |
| url |
http://hdl.handle.net/10361/17213 |
| work_keys_str_mv |
AT fihayeaminjahan performanceanalysisofdeeplearningalgorithmsforintrusiondetectionsystemidsofiotsecurity AT farjanamithila performanceanalysisofdeeplearningalgorithmsforintrusiondetectionsystemidsofiotsecurity AT binmasumsyedrifat performanceanalysisofdeeplearningalgorithmsforintrusiondetectionsystemidsofiotsecurity AT soronmehedibinsarwar performanceanalysisofdeeplearningalgorithmsforintrusiondetectionsystemidsofiotsecurity AT alifmiafahimhasan performanceanalysisofdeeplearningalgorithmsforintrusiondetectionsystemidsofiotsecurity |
| _version_ |
1814308897512488960 |
| spelling |
10361-172132022-09-13T21:01:44Z Performance analysis of deep learning algorithms for Intrusion Detection System(IDS) of IoT Security Fiha, Yeamin Jahan Farjana, Mithila Bin Masum, Syed Rifat Soron, Mehedi Bin Sarwar Alif, Mia Fahim Hasan Hossain, Muhammad Iqbal Bin Ashraf, Mr. Faisal Department of Computer Science and Engineering, Brac University Deep learning Intrusion Detection System IoT Security RNN GRU LSTM KDD-99 NSL-KDD LSTM GRU IDS Vanilla LSTM Bidirectional LSTM Stacked LSTM Machine learning. Intrusion detection systems (Computer security) Internet of things This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2022. Cataloged from PDF version of thesis. Includes bibliographical references (pages 41-43). The Internet of Things (IoT) is a term that refers to billions of actual gadgets all over the universe that are connected to the network, participating in all social events, and sharing data. It is the most recent technological advancement in history. In addition, Internet of Things devices have sensors and small PC processors that generate applications based on the data gathered by the sensors through Artificial Intelligence (AI). Fundamentally, Internet of Things (IoT) devices are more modest than anticipated PCs, are connected to the internet, and are vulnerable to viruses and hacking. Similarly, there are legitimate concerns about risks associated with the expansion of the Internet of Things, notably in the areas of safety and security. Nowadays, the intrusion detection system for Internet of Things devices is a critical concern. Entering the computer environment is an extremely dangerous and unpredictable activity that has existed since the invention of computer technology. Many security measures have been implemented over the past three decades, but as technology has progressed, so have the threats to national security. Because the world is increasingly reliant on computers, whether directly or indirectly, it is critical to prevent potentially dangerous activities and attacks that could jeopardize com puter infrastructure. IDS and IPS are two often used security solutions to protect computer resources, particularly those on a network. To create a secure Internet of Things deployment, a variety of security principles need to be followed at each tier. In this case, the impact of artificial intelligence on the internet security of Internet of Things devices is likely to alter the traditional risk assessments. Aside from that, the field of Artificial Intelligence (AI) is rapidly expanding, propelled by shifts in neuron organization and deep learning. In addition to this, we have employed Deep Learning Approach to detect the intrusion of IoT gadgets as well as other types of intrusion. Deep Learning is a sub-sector of artificial intelligence and machine learning (ML) that mimics the way the human brain works in terms of data pro cessing and making effective decisions. As a result, it is playing an important role in the detection of intrusion from devices that are linked to the internet. The IDS (Intrusion Detection System) of Internet of Things System utilizing Deep Learning techniques is the subject of our thesis. Our article provides a complete analysis of security policies, technical obstacles, and solutions for Internet of Things (IoT) se curity protection. In addition, we have employed two datasets, namely KDD-99 and NSL-KDD, as well as three methods, including RNN, LSTM, and GRU, in our pa per. The proposed model was tested and evaluated as a consequence, and the results demonstrate that the model is extremely accurate when it comes to distinguishing interruptions in Internet of Things devices.. Yeamin Jahan Fiha Mithila Farjana Syed Rifat Bin Masum Mehedi Bin Sarwar Soron Mia Fahim Hasan Ali B. Computer Science 2022-09-13T09:16:14Z 2022-09-13T09:16:14Z 2022 2022-01 Thesis ID: 17101475 ID: 17201042 ID: 17201063 ID: 17201064 ID: 17301206 http://hdl.handle.net/10361/17213 en_US Brac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. 43 pages application/pdf Brac University |