Enhanced Hybrid Deep Learning Approach for Botnet Attacks Detection in IoT Environment

2024-11-12

2024 7th International Conference on Signal Processing and Information Security (ICSPIS)

AI Summary

Addressing the challenge of detecting stealthy, dynamically evolving botnet attacks in Internet-of-Things (IoT) environments, this paper proposes a novel four-model collaborative stacking architecture integrating CNN, Bi-LSTM, Bi-GRU, and RNN. The design jointly captures local spatial features and bidirectional temporal dependencies to enable fine-grained representation and real-time detection of network traffic behavior. To our knowledge, this is the first work to introduce a heterogeneous multi-model stacking mechanism, significantly enhancing discriminative capability for low signal-to-noise-ratio and short-duration botnet traffic. Evaluated on the UNSW-NB15 dataset, the model achieves 99.76% accuracy and 99.18% ROC-AUC—surpassing existing state-of-the-art methods. The approach offers a highly robust, deployable detection paradigm for IoT security, balancing modeling expressiveness with practical applicability.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Learning on the Edge & Model Compression
• Natural Language Processing: Safety and Robustness

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Models for Web evolution

Abstract

Cyberattacks in an Internet of Things (IoT) environment can have significant impacts because of the interconnected nature of devices and systems. An attacker uses a network of compromised IoT devices in a botnet attack to carry out various harmful activities. Detecting botnet attacks poses several challenges because of the intricate and evolving nature of these threats. Botnet attacks erode trust in IoT devices and systems, undermining confidence in their security, reliability, and integrity. Deep learning techniques have significantly enhanced the detection of botnet attacks due to their ability to analyze and learn from complex patterns in data. This research proposed the stacking of Deep convolutional neural networks, Bi-Directional Long Short-Term Memory (Bi-LSTM), Bi-Directional Gated Recurrent Unit (Bi-GRU), and Recurrent Neural Networks (RNN) for botnet attacks detection. The UNSW-NB15 dataset is utilized for botnet attacks detection. According to experimental results, the proposed model accurately provides for the intricate patterns and features of botnet attacks, with a testing accuracy of ${9 9. 7 6 %}$. The proposed model also identifies botnets with a high ROC-AUC curve value of ${9 9. 1 8 %}$. A performance comparison of the proposed method with existing state-of-the-art models confirms its higher performance. The outcomes of this research could strengthen cyber security procedures and safeguard against new attacks.

Problem

• Detects botnet attacks in IoT environments
• Utilizes deep learning for complex pattern analysis
• Enhances cybersecurity with high detection accuracy

Innovation

• Hybrid deep learning model
• Stacking multiple neural networks
• High accuracy botnet detection