Proposed a novel model-free label-flipping attack based on the multi-modality of the data and a novel defense technique based on the Synthetic Reduced Nearest Neighbor (SRNN) model. A preprint copy […]
Read MoreSAIL Lab in collaboration with Enterprise Model Risk Management Group, Royal Bank of Canada (RBC) did research project on Deep Reinforcement Learning(DRL). The paper titled “Adversarial Attacks on Deep Algorithmic […]
Read MoreMilan Zinzuvadiya’s research work under the supervision of Dr. Behzadan, titled “State-Wise Adaptive Discounting from Experience (SADE): A Novel Discounting Scheme for Reinforcement Learning” has been accepted by AAAI Conference […]
Read More