| |
 | | | Causality Analysis for Neural Network Security |  | SUN Bing PhD Candidate
School of Computing and Information Systems
Singapore Management University
| Research Area Dissertation Committee Research Advisor Co-Research Advisor Dissertation Committee Member External Member - XIAO Xiaokui, Professor, School of Computing, National University of Singapore
|
| | Date 12 December 2024 (Thursday) | Time 10:00am – 11:00am | Venue Meeting room 5.1,
Level 5
School of Computing and Information Systems 1,
Singapore Management University,
80 Stamford Road,
Singapore 178902 | Please register by 11 December 2024. We look forward to seeing you at this research seminar. 
|
|
|
| | ABOUT THE TALK While neural networks are demonstrating excellent performance in a wide range of applications, there has been a growing concern on their reliability and dependability. Similar to traditional decision-making programs, neural networks inevitably have defects that need to be identified and mitigated at times. Neural networks are usually inherently black-boxes and do not provide explanations on how and why decisions are made. As a result, these defects are more ``hidden" and more challenging to eliminate. It is thus crucial to develop systematic approaches to identify and mitigate defects in a neural network in a rigorous way. In this dissertation, we focus on three important properties of neural networks, fairness, backdoor-freeness and robustness, and develop systematic ways to mitigate the risk of discrimination, having backdoors and adversarial perturbations. | | | ABOUT THE SPEAKER Bing SUN specializes in AI security research, focusing on areas such as neural network fairness, robustness, and defenses against backdoor attacks. Prior to joining SMU, she earned a Master's degree in Computer Control and Automation as well as a Bachelor's degree in Electrical and Electronic Engineering, both from NTU. In her free time, SUN enjoys traveling and engaging in sports. |
|
