|
Document Type |
: |
Thesis |
|
Document Title |
: |
EMERGING SECURITY ATTACK DETECTION USING CAPSULE NEURAL NETWORK كشف الهجوم الأمني الناشئ باستخدام شبكة الكبسولة العصبية |
|
Subject |
: |
Faculty of Computing and Information Technology |
|
Document Language |
: |
Arabic |
|
Abstract |
: |
In cybersecurity, analyzing social network data has become an essential research area due to its property of providing real-time updates about real-world events. Studies have shown that Twitter can contain information about security threats before some specialized sites. Thus, the classification of tweets into security-related and not security-related can help with early warnings for such attacks. Many techniques for text classification using different traditional machine learning (ML), neural network (NN), and deep learning (DL) algorithms have been widely investigated for detecting cyber-attacks using Twitter data. Convolutional neural network (CNN) and recurrent neural network (RNN) are two of the most recent and advanced techniques. However, CNN and RNN suffer from limitations related to its architectures which lead to proposing the capsule network (CapsNet). In this study, we investigated the use of the CapsNet, the new DL algorithm, for the first time in the field of security attack detection using Twitter. We aim to increase the accuracy of tweet classification by using CapsNet rather than CNN or RNN. To achieve the research objective, we adapted the original implementation of CapsNet to be compatible with the tweet dataset. A random search technique was used to tune the model’s hyperparameters. A series of experiments and comparisons were conducted to evaluate the research contribution efficiency. The experimental results showed that CapsNet exceeded the baseline CNN, and CNN and RNN previous works on the same dataset, with accuracy of 92.21% and a 92.2% F1-score using word2vec embedding. Besides, in all experiments, the word2vec embedding performed better than a random initialization. |
|
Supervisor |
: |
Dr. Maysoon Abulkhair |
|
Thesis Type |
: |
Master Thesis |
|
Publishing Year |
: |
1442 AH
2020 AD |
|
Co-Supervisor |
: |
Dr. Entisar Alkayal |
|
Added Date |
: |
Sunday, August 23, 2020 |
|
Researchers
| سحر جبير الطلحي | Altalhi, Sahar Jubair | Researcher | Master | |
|