Enhancing IoT Forensics through Deep Learning: Investigating Cyber-Attacks and Analyzing Big Data for Improved Security Measures

This paper discovers IoT (Internet of Things) forensics and how the deep learning is improving the efficiency of digital investigations. With the exponential growing of IoT, effective security measures and protocols are obligatory to protect from cyber risks and threats. However, IoT devices are remain vulnerable to attacks, So, this led us to data breaches, loss of privacy, and other harmful consequences. IoT forensics is investigates and analyzes digital evidences related to IoT devices and then identify the source of cyber-attack. This paper has been discussed the fundamentals’ of IoT forensics also the important role it plays in the realm of cybersecurity. Furthermore, this paper explores the different kinds of IoT datasets and how we can automate the analysis of big data by using deep learning. Also, it helps in identify potential sources of evidence, and construct predictive models to prevent future attacks. The paper also shows experiments of two deep learning models, LSTM and RNN, on a binary, 6 class, and 15 class classification. Different evaluation metrics have been used like: precision, recall, F1-score, and ROC which allow investigators to objectively evaluate the forensic model’s effectiveness. The Edge-IIoTset dataset developers who used deep neural networks (DNNs) were compared to the research findings, and it was discovered that the RNN model with the given architecture behaved the best on the dataset.