Synthesizing Robust Adversarial Examples
Anish Athalye, Logan Engstrom, Andrew Ilyas et al. · arXiv (Cornell University) · 2017
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.
Cited by 625 works. doi:10.48550/arxiv.1707.07397 Open-access PDF
Authors
References
- Rethinking the Inception Architecture for Computer Vision
- Intriguing properties of neural networks
- Towards Evaluating the Robustness of Neural Networks
- The Limitations of Deep Learning in Adversarial Settings
- DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks
- Adversarial Examples in the Physical World
- Distillation as a Defense to Adversarial Perturbations Against Deep Neural Networks
- Practical Black-Box Attacks against Machine Learning
- Universal Adversarial Perturbations
- Evasion attacks against machine learning at test time