I am a Postdoctoral Researcher at the University of Tokyo, hosted by Prof. Masashi Sugiyama.
My research mainly focuses on trustworthy machine learning, especially adversarial learning and data security.
Email to: firstname.lastname@example.org
Adversarial Neuron Pruning Purifies Backdoored Deep ModelsIn NeurIPS, 2021
Adversarial Weight Perturbation Helps Robust GeneralizationIn NeurIPS, 2020
Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResnetsIn ICLR Spotlight, 2020