Robustness of classifiers to uniform $\ell \_p$ and Gaussian noise

Abstract

We study the robustness of classifiers to various kinds of random noise models. In particular, we consider noise drawn uniformly from the $\ell \_p$ ball for $p\in [1,\infty ]$ and Gaussian noise with an arbitrary covariance matrix. We characterize this robustness to random noise in terms of the distance to the decision boundary of the classifier. This analysis applies to linear classifiers as well as classifiers with locally approximately flat decision boundaries, a condition which is satisfied by state-of-the-art deep neural networks. The predicted robustness is verified experimentally.

References in corpus (2)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• A Boundary Tilting Persepective on the Phenomenon of Adversarial Examples

Cited by in corpus (5)

• Robust sound event detection in bioacoustic sensor networks
• A Review of Adversarial Attack and Defense for Classification Methods
• Identifying Classes Susceptible to Adversarial Attacks
• PROVEN: Certifying Robustness of Neural Networks with a Probabilistic Approach
• Certifying Neural Network Robustness to Random Input Noise from Samples