Trustworthy Intelligent Computing
A trustworthy system does what its legal users expect it to do – and not something else – despite environmental disruption, impairments caused by itself, human users and operators, and potential attacks by hostile parties. Design and implementation of errors must be avoided, eliminated, or somehow tolerated. It is not sufficient to address only some of these dimensions, nor is it sufficient simply to assemble components that are themselves trustworthy. Thus, trustworthiness is multi-facetted and holistic.
Intelligent computing aims to integrate systems to perceive, reason, learn, and act intelligently in the real world. As the real world data and processes are dynamic and stochastic, an intelligent system has to deal with large volumes of data, occasional updates to the data by the users, and unexpected changes in data distributions due to nuisance factors. Therefore, the design of such systems involves hard scalability and robustness constraints that needs to be satisfied.
Accordingly, our research areas include but are not limited to the following topics.