The objective of this course is to provide students with the fundamental elements of AI security in the context of different application domains. The main concepts and methods of adversarial machine learning are presented, from threat modeling to attacks and defenses, as well as basic methods to properly evaluate adversarial robustness of an AI model against different attacks. The module also encompasses advanced topics related to real-world scenarios, examining how AI systems are utilized in processing image, audio, and video data, which will illuminate both the challenges and solutions in ensuring AI security.
A Demonstrate practical knowledge of deep learning robustness. B Demonstrate awareness of potential security, equality, legal and ethics issues. C Recognise the security risks that may be involved in AI systems. D Evaluate, design and implement AI security systems.
This module will be delivered through a combination of formal lectures, tutorials, and Coursework.