• Sivananda Hanumanthu
• G. Anil Kumar

Abstract: Cyberattack detection becomes more complex for the existing models to find the attack patterns in the early stages. The traditional Intrusion Detection System (IDS) cannot adapt to the dynamic and changing attack patterns provided in the IoT environment. In this work, we present a deep learning-based architecture using Adaptive Convolutional Neural Networks (CNNs) to detect cyber-attacks on IoT use cases automatically. The proposed model can quickly identify multiple forms of cyber threats by applying deep learning (DL) methods to extract spatial-temporal features from the traffic data. Based on data of possible attack patterns, we use feature engineering techniques to preprocess the dataset and have accordingly optimized a CNN-based architecture suitable for IoT-related anomalies. We validate our framework on benchmark IoT attack datasets and show that our approach achieves better detection performance than standard machine learning techniques. The model has obtained superior performance based on experimental results, indicating it is a potential solution for future real-time intrusion detection in IoT networks.

Intrusion Detection System (IDS), CyberAttacks, Cybersecurity.

"Enhanced Cyberattack Detection in IoT Networks Using a Convolutional Neural Network (CNN) Framework", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 3, page no.d1-d6, March-2025, Available :http://www.jetir.org/papers/JETIR2503301.pdf

"Enhanced Cyberattack Detection in IoT Networks Using a Convolutional Neural Network (CNN) Framework", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 3, page no. ppd1-d6, March-2025, Available at : http://www.jetir.org/papers/JETIR2503301.pdf