PhD Dissertation Proposal by SUN Bing | Causality Analysis for Neural Network Security

Neural networks have had discernible achievements in a wide range of applications. While neural networks are demonstrating excellent performance, there has been a growing concern on whether they are reliable and dependable. Similar to traditional decision-making programs, neural networks inevitably have defects that need to be identified and mitigated at times. It is thus crucial to develop systematic approaches to identify and mitigate defects in a neural network in a rigorous way while its desirable properties are maintained. In this dissertation, we focus on three important properties of neural networks, fairness, backdoor-freeness and robustness, and develop system ways to mitigate the risk of discrimination, having backdoors and adversarial perturbations.

Sun Bing is a Ph.D candidate in SMU SCIS, supervised by Prof. Sun Jun and co-supervised by Prof Robert Deng. Sun Bing’s research focuses on neural network security.