A Robust Framework for Detecting Brute-Force Attacks through Deep Learning Techniques
Nouf Awadh¹, Hawazen Zaid², Samah Al-ajmani³

¹Nouf Awadh, College of Computers and Information Technology, Taif University, Taif, SA.

²Hawazen Zaid, College of Computers and Information Technology, Taif University, Taif, SA.

³Dr. Samah Al-ajmani, Department of Information Technology, College of Computer and Information Technology, Taif University, Taif, SA.  

Manuscript received on 31 October 2024 | First Revised Manuscript received on 10 December 2024 | Second Revised Manuscript received on 17 December 2024 | Manuscript Accepted on 15 January 2025 | Manuscript published on 30 January 2025 | PP: 27-42 | Volume-13 Issue-5, January 2025 | Retrieval Number: 100.1/ijrte.E818213050125 | DOI: 10.35940/ijrte.E8182.13050125

Open Access | Editorial and Publishing Policies | Cite | Zenodo | OJS | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract:  A considerable concern arises with the precise identification of brute-force threats within a networked environment. It emphasises the need for new methods, as existing ones often result in numerous false alarms and delays in real-time threat detection. To tackle these issues, this study proposes a novel intrusion detection framework that utilizes deep learning models for more accurate and efficient detection of brute-force attacks. The framework’s structure includes data collection and preprocessing components performed at the outset of the study using the CSE-CICIDS2018 dataset. The design architecture comprises data collection and preprocessing steps. Feature extraction and selection techniques are employed to optimize data for model training. Furthermore, after building the model, various attributes are extracted from the data through feature selection for use in training. Then, the construction of multiple architectures of deep learning algorithms, which include Artificial Neural Networks (ANN), Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), and Long Short-Term Memory (LSTM) models. Evaluation results show that CNN and LSTM achieved the highest accuracy of 99.995% and 99.99%, respectively. It showcases its ability to detect complex attack patterns in network traffic. It indicates that the CNN network got the best optimum results with a test time of 9.94 seconds. This establishes CNN as an effective method, achieving high accuracy quickly. In comparison, we have surpassed the accuracy of current methods while addressing their weaknesses. The findings are consistent with the effectiveness of CNN in brute-force attack detection frameworks as a more accurate and faster alternative, thereby increasing the capability to detect intrusions on a network in real-time.

Keywords: Deep Learning, Brute Force Attack, IDS, CSE-CICIDS2018.
Scope of the Article: Artificial Intelligence and Methods