Synthesizing Robust Adversarial Examples

[edit]

Anish Athalye, Logan Engstrom, Andrew Ilyas, Kevin Kwok ;
Proceedings of the 35th International Conference on Machine Learning, PMLR 80:284-293, 2018.

Abstract

Standard methods for generating adversarial examples for neural networks do not consistently fool neural network classifiers in the physical world due to a combination of viewpoint shifts, camera noise, and other natural transformations, limiting their relevance to real-world systems. We demonstrate the existence of robust 3D adversarial objects, and we present the first algorithm for synthesizing examples that are adversarial over a chosen distribution of transformations. We synthesize two-dimensional adversarial images that are robust to noise, distortion, and affine transformation. We apply our algorithm to complex three-dimensional objects, using 3D-printing to manufacture the first physical adversarial objects. Our results demonstrate the existence of 3D adversarial objects in the physical world.

Related Material