A Tutorial On Attacking Dnns Using Adversarial Examples

Summary

This video was recorded as part of CIS 522 - Deep Learning at the University of Pennsylvania. The course material, including Workshop posters: - github.com/anlthms/nips-2017/blob/master/poster/ Adnan Rakin (Arizona State University, former MERL intern) presents our paper "Towards Universal You know we can hack a neural network just feed an image of a cat to a neural network and it predicts When Deep Neural Networks go wrong – Outline: 00:00 - Context and Motivations 06:24 - Background 15:08 - Related Works 25:02 - Proposed approach 39:50 ... Hint: Stay until the end of the video for an Authors: Chaoning Zhang, Philipp Benz, Tooba Imtiaz, In So Kweon Description: A wide variety of works have explored the reason ... Artificial neural networks are computer programs that try to approximate what the human brain does to solve problems  ... Nicolas Papernot, Director of Institute for Network and Security Research, and Patrick McDaniel, Computer Security Graduate ... Attackers are taking advantage of weaknesses in the Authors: Akhil Goel, Akshay Agarwal, Mayank Vatsa, Richa Singh, Nalini K. Ratha Description: Several successful Authors: Mingyi Zhou, Jing Wu, Yipeng Liu, Shuaicheng Liu, Ce Zhu Description: Machine learning models are vulnerable to ...