The purpose chapter objectives to design a scalable and intelligent threat detection system to smart policing networks that leverages the IoT technology at scale. It will deal with the problems of timely processing of data of various types of devices and security issues related to such devices. It is suggested to use a multi-layer architecture based on multi-modal (different forms of media) deep learning, near the source (edge) processing of data as well as federated (distributed) learning to provide/network intelligence to the threat detection system. The system is a combination of CNN-BLSTM-based feature learning and adaptive decision mechanisms to allow real-time detection and response. The hybrid dataset of benchmark intrusion data, real IoT traffic, and simulated attack scenarios are used to validate this experiment. The proposed framework has a high detection accuracy (96.7%) and low latency (~280 ms), which is better than the traditional, machine learning, and state-of-the-art deep learning models.
Megha Mudholkar, Pankaj Mudholkar, Prasuna Kotturu et al.· Advances in wireless technol...· 0 citations
The excessive proliferation of Internet of Things (IoT) ecosystems, which are characterized by the high number of devices, transient data generation, and constantly changing cyber threats have presented serious challenges to digital forensic investigations. To solve these problems, Adaptive Forensic Intelligence Model (AFIM) is suggested as a combined model. AFIM is a multi-modal evidence-gathering mechanism, a blockchain-based secure evidence management mechanism, and an AI-based forensic analytics engine. The model has been experimentally tested on a hybrid dataset of real data of the IoT and simulated cyberattack scenarios. The federated learning framework enables models to be developed in a decentralized manner as well as using adaptive thresholding for anomaly detection “on the fly”, thereby creating scalable and resilient systems to operate in distributed environments.
Meenakshi Gupta, R. Udaya Bharathi, Subarno Bhattacharyya et al.· Advances in wireless technol...· 0 citations
The chapter tries to resolve this emerging problem of machine learning-based smart heterogeneous networks, and cybersecurity by creating a multi-layered security infrastructure which is scalable to detect and react to security attacks in real-time. It proposes a multi-modal deep learning (CNNLSTM), adaptive control by reinforcement learning, and privacy-sensitive controls, such as federated learning. Heterogeneous datasets, including the IoT traffic, intrusion detection benchmarks, and multi-step attack scenarios, which are synthetic, are trained and tested with the model. The accuracy, precision, recall, F1-score, AUC-ROC, and the computational efficiency metrics are used to measure the performance in dynamic and noisy settings. The suggested framework is also a better performer than the baseline models, where accuracy is 98.37 and has a better ability to resist multi-step and evolving cyber threats. Integration of reinforcement learning increases adaptability and multi-modal features fusion increases detection accuracy.
Harish Reddy Gantla, N. Thangadurai, Manikandan Hariharan et al.· Advances in wireless technol...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
