I am a PhD student affiliated with UvA-Bosch Delta Lab at the University of Amsterdam. I am currently working on explaining the images near the boundary. The images near the boundary we are considering are adversarial examples and hard positive/negative examples. Our end goal is to make classifiers robust against adversarial examples.
Before joining UvA-Bosch Delta Lab I completed my Masters in Electrical Engineering from Korea Advanced Institute of Science and Technology (KAIST). My research interests include domain adaptation, explainable AI, Adversarial examples, Zero-shot learning.