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
Most existing systems have sufficient data integrity but lack appropriate communication and decision-making methods that allow for timely responses to change. This paper discusses the use of a blockchain-based design as a method for overcoming these limitations by utilizing secure communication protocols and smart evidence management to support electronic evidence. An architecture based on multi-layers is constructed on top of blockchain, cryptographic encoding, hybrid storage (blockchain + IPFS) and a reinforcement learning-based adaptive component. The system is experimentally tested on both simulated and real-world digital evidence sets in different network loads, and attack conditions. The use of metrics like integrity accuracy, communication reliability, latency and scalability is used to measure performance. The proposed framework has high integrity preservation (>99%), enhanced the reliability of communications, and less latency as compared to baseline systems. The hybrid architecture can be used successfully to reduce the storage overheads.
Divyanshu Sinha, Hastimal Jangid, G. Radha Krishna Murthy 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.
