Our research delves into the intersection of software engineering, security and machine learning. While machine learning-based techniques have been widely applied in security domains, being able to explain the rationale behind their decision making process remains as a largely open problem. The inherent nature of security research requires us to understand the intrinsic characteristics of a neural network model instead of just parts of model behaviors. Our research is motivated to explain the rationale behind decision making process of machine learning-based techniques in security domains.
Investigating the robustness of neural networks against energy-oriented attacks. ILFO is Adversarial Attack on Adaptive Neural Networks