Addressing Security and Privacy Issues by Analyzing Vulnerabilities in IoT Applications
Abstract
The Internet of Things (IoT) environment has been expanding rapidly for the past few years into several areas of our lives, from factories, to stores and even into our own homes. All these new devices in our homes make our day-to-day lives easier and more comfortable with less effort on our part, converting our simple houses into smart homes. This increase in inter-connectivity brings multiple benefits including the improvement in energy efficiency in our homes, however it also brings with it some potential dangers since more points of connection mean more potential vulnerabilities in our grid. These vulnerabilities bring security and privacy concerns into our day-to-day lives. The more devices inside a house, the more information can be collected about the people living there. Naturally, people can be concerned about how attackers could acquire their information and feel hesitant about the inclusion of IoT devices inside their home despite the clear benefits it can bring to them. Even though this is a clear issue for the community, smart home cybersecurity is still in its infant stage. The purpose of this thesis is to improve upon smart-home cybersecurity techniques to provide a more secure environment that will protect the users’ privacy while maintaining a fast response time. This is aimed to be done with a dual approach; a cryptographic approached based on elliptic curve cryptography and Blake2 hashing, and a non-cryptographic approach based on synthetic data generation using a specific type of neural network called Generative Adversarial Network (GAN), which will create adversarial traffic for an Intrusion Detection System (IDS) to train on and improve its accuracy and decrease the number of false negatives. This encryption technique is tested upon a smart home environment with a Raspberry Pi as a control hub. Once these techniques are refined, they can be fully implemented on smart home devices and even moved into an industrial control system environment.
Subject Area
Computer Engineering|Cognitive psychology|Artificial intelligence
Recommended Citation
Candelario Burgoa, Francsico Javier, "Addressing Security and Privacy Issues by Analyzing Vulnerabilities in IoT Applications" (2021). ETD Collection for University of Texas, El Paso. AAI28866519.
https://scholarworks.utep.edu/dissertations/AAI28866519