%0 Journal Article %1 athalye2017synthesizing %A Athalye, Anish %A Engstrom, Logan %A Ilyas, Andrew %A Kwok, Kevin %D 2017 %K adversarial generalization readings %T Synthesizing Robust Adversarial Examples %U http://arxiv.org/abs/1707.07397 %X 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.

@article{athalye2017synthesizing, 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.}, added-at = {2019-10-18T14:29:05.000+0200}, author = {Athalye, Anish and Engstrom, Logan and Ilyas, Andrew and Kwok, Kevin}, biburl = {https://www.bibsonomy.org/bibtex/26e1f2c599b3fb9fa444b791961b01726/kirk86}, description = {[1707.07397] Synthesizing Robust Adversarial Examples}, interhash = {bccdb226d746e91a31694fe919fa8c66}, intrahash = {6e1f2c599b3fb9fa444b791961b01726}, keywords = {adversarial generalization readings}, note = {cite arxiv:1707.07397Comment: ICML 2018}, timestamp = {2019-10-18T14:29:05.000+0200}, title = {Synthesizing Robust Adversarial Examples}, url = {http://arxiv.org/abs/1707.07397}, year = 2017 }