Robust Defenses Against Adversarial Machine Learning in IoT Security
Olakunle Ibitoye · 2024
The cybersecurity of the Internet of Things (IoT) has been poised to benefit from Artificial Intelligence (AI).Advances such as AI-based Intrusion detection systems for IoT have shown promising results.However, these advances have been set back by the rise of Adversarial Samples.Adversarial Samples are specially crafted data samples that are designed to mislead an AI model into making a wrong prediction.When subjected to Adversarial Samples, AI models that have been optimally trained to make accurate predictions, will produce incorrect results.In this thesis document, we explore the reasons behind the vulnerability of AI models to Adversarial Samples.We also propose novel methods for addressing the challenge of Adversarial Samples in the specific context of cybersecurity applications for IoT.I would like to express my deepest appreciation to my PhD supervisors Dr. M. Omair Shafiq and Dr. Ashraf Matrawy for their guidance throughout the journey.Words cannot express my gratitude to the chair of my committee for the invaluable patience and feedback.I also could