Vulnerability of Deep Networks, by Venkatesh Babu
Deep learning has significantly changed computer vision research. Deep models have achieved state of the art performance in almost all vision tasks. Though Deep models show human level performance across many inference tasks, they are shown to be vulnerable to adversarial noise: small but structured perturbation added to the input that affects the model’s prediction drastically. This talk will briefly outline various ways of crafting such adversarial perturbations.
About the speaker
R. Venkatesh Babu is an associate professor in Department of Computational and Data Sciences, Indian Institute of Science, Bangalore. He received his Ph.D. degree from the Dept. of Electrical Engineering, Indian Institute of Science, Bangalore. He held postdoctoral positions at NTNU, Norway, IRISA/INRIA, France and NTU, Singapore. He spent couple of years working in industry before joining IISc in 2010. His research interests span computer vision, machine learning and signal processing. He is the convener of Video Analytics Lab at IISc and a senior member of IEEE.