Year: 2024
Type: article
Abstract: The rapid proliferation of Internet of Things (IoT) devices has expanded the digital ecosystem, offering unprecedented connectivity while simultaneously increasing vulnerability to cyber threats. Investigating cybercrimes in IoT environments is challenging due to the heterogeneous nature of devices, the massive volume of data generated, and the complexity of attack vectors. This paper introduces a novel forensic investigation framework that integrates big data analytics and deep learning-based feature fusion to address these challenges. The framework processes multi-modal IoT data, leveraging advanced deep learning models such as convolutional neural networks (CNNs), long short-term memory (LSTM) networks, and autoencoders for feature extraction and fusion. A feature fusion layer combines insights from diverse data sources, enhancing forensic accuracy and enabling efficient cybercrime reconstruction. Experimental results demonstrate that the proposed approach outperforms traditional methods in terms of detection accuracy, scalability, and processing efficiency. This work underscores the potential of integrating big data and deep learning in cyber forensic investigations, paving the way for more robust and scalable IoT forensic solutions.
Author: Dr. Suman Thapaliya
Institution: Lincoln University College
Language: English
Topic: Digital and Cyber Forensics
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W4405596231