Leveraging Machine Learning for Anomaly Detection and Pattern Recognition in IoT Forensics
Open Access DepositedIn modern days Internet of Things (IoT) devices are multiplying at an exponential rate, the amount of data being generated through these devices is also increasing rapidly (Atzori et al., 2010). In the coming years the security threats created by IoT devices will be overwhelming. IoT devices are vulnerable to security threats, including but not limited to data breaches, unauthorized access, and malware attacks (Sicari et al., 2015). This study investigates how machine learning can help detect and decipher these dangers in the enormous space of IoT data.This study examines the use of unsupervised machine learning techniques to detect anomalies and recognize patterns that indicate cyber threats automatically, without pre-defined labels or training data. We will explore clustering algorithms such as the K-Means, Density-Based Spatial Clustering of Applications with Noise (DBSCAN), MiniBatchKMeans, Gaussian Mixture Models (GMM), and Balanced Iterative Reducing and Clustering using Hierarchies (BIRCH). Autoencoders and Principal Component Analysis (PCA) algorithms are used to assess their efficiency in differentiating among large, heterogeneous datasets and spotting anomalies which could assist in a security breach. This research will be able to assist experts in cyber-crime investigation in identifying malicious devices from a given IoT network. These results may set the stage for future possibilities and the development of more real-time, adaptive security functions for the ever-growing and changing IoT device universe.
- All rights reserved
Notice to Authors
If you are the author of this work and you have any questions about the information on this page, please use the Contact form to get in touch with us.
| Thumbnail | Title | Date Uploaded | Visibility | Actions |
|---|---|---|---|---|
|
|
Alemayehu_gwu_0075A_17549.pdf | 2025-12-11 | Open Access |
|