tensorflow-for-deep-learning-py/Papers/Adversarial_examples_1607.02533v1.md

Adversarial Examples in the Physical World

Kurakin, Goodfellow, Bengio

http://arxiv.org/pdf/1607.02533v1.pdf

• An adversarial example is a sample of input data which has been modified very slightly in a way that is intended to cause a machine learning classifier to misclassify it.

• Adversarial examples pose security concerns because they could be used to perform an attack on machine learning systems, even if the adversary has no access to the underlying model