AI Safety and Security

The aim of this project is to employ rigorous software engineering principles for designing robust decision making systems (e.g. robust and secure artificial intelligent and machine-learning systems). To this end, we focus on various desirable properties of decision making systems, including but not limited to security (e.g. resilience against adversarial and backdoor attacks), robustness and fairness (i.e. removing social discrimination). Another focus of the project is the systematic usage of artificial intelligent (AI) systems to detect cyber attacks and explain their cause. To know more about the topic, take a look at the following publications: ASE-2018, Arxiv-2019-OGMA, Arxiv-2019-NEO, EMSOFT-WiP-2018, Arxiv-2019-RAIDS.

Acknowledgement: We are grateful to National Research Foundations, Singapore for generously supporting this project.

People

Chundong Wang
Post Doc (PhD, NUS, Singapore)
Sakshi Udeshi
PhD Student (SUTD)
Jia Yifan
PhD Student (SUTD and TUV SUD)