Exploring the Role of Mining Wireless Framework in Identifying Human Privacy Vulnerabilities in Internet of Things Networks

One of the most promising technologies with global impact is the Internet of Things (IoT). As IoT systems continue to mature and be implemented, they have the potential to profoundly alter how human societies produce goods, conduct business, and live their daily lives. The number of active Internet of Things gadgets and software has increased exponentially during the last few years. People appreciate IoT's advantages, but its security and privacy concerns are not being addressed at the same rate as the technology itself is progressing. Our research shows that even when wireless IoT communication is encrypted, sensitive user data may be leaked. Using a wireless sniffer stationed outside the user's home, we may infer the user's activities while at home. In this research, we offer a strategy for wireless eavesdropping that may be used too many forms of user privacy. Initially, we identify IoT events by extracting characteristics from the packet sequence. Then, we deduce the user's actions and, in certain cases, their emotional state based on the identified IoT occurrence. In addition, we may deduce the user's lifestyle, and IoT apps by studying the wireless context, which is uncovered by mining thedependencies of the IoT. By disclosing this information, the user's privacy is violated, and the attack surface that an attacker may exploit to take control of the smart home is widened. We use the SmartThings platform to test our eavesdropping methodology and apply it. The results show that our eavesdropping method is both practical and efficient.