Thesis Title
Evaluation of Adversarial Attacks and Bias in Deep Neural Networks

Research Description
Afsaneh’s research focuses on enhancing the robustness of deep learning models against adversarial attacks, with a strong interest in model fairness and interoperability. By improving these aspects, she aims to increase the trustworthiness of AI models, which is crucial in today’s world where the reliance on AI continues to grow.

Supervisors
Prof Christopher Leckie, University of Melbourne
Prof Sarah Erfani, University of Melbourne