Adversarial Examples Are Not Bugs, They Are Features
Abstract:
Adversarial examples have attracted significant attention in machine learning, but the reasons for their existence and pervasiveness remain unclear. We demonstrate that adversarial examples can be directly attributed to the presence of non-robust features: features derived from patterns in the data distribution that are highly predictive, yet brittle and incomprehensible to humans. After capturing these features within a theoretical framework, we establish their widespread existence in standard datasets. Finally, we present a simple setting where we can rigorously tie the phenomena we observe in practice to a misalignment between the (human-specified) notion of robustness and the inherent geometry of the data.
Authors: Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras, Logan Engstrom, Brandon Tran, Aleksander Madry
https://arxiv.org/abs/1905.02175
Watch video Adversarial Examples Are Not Bugs, They Are Features online without registration, duration hours minute second in high quality. This video was added by user Yannic Kilcher 14 May 2019, don't forget to share it with your friends and acquaintances, it has been viewed on our site 11,916 once and liked it 400 people.