Colored Noise Injection for Training Adversarially Robust Neural Networks

Evgenii Zheltonozhskii, Chaim Baskin, Yaniv Nemcovsky, Brian Chmiel, Avi Mendelson, Alexander Bronstein

Research output: Working paperPreprint


Even though deep learning has shown unmatched performance on various tasks, neural networks have been shown to be vulnerable to small adversarial perturbations of the input that lead to significant performance degradation. In this work we extend the idea of adding white Gaussian noise to the network weights and activations during adversarial training (PNI [7]) to the injection of colored noise for defense against common white-box and black-box attacks. We show that our approach outperforms PNI and various previous approaches in terms of adversarial accuracy on CIFAR-10 and CIFAR-100 datasets. In addition, we provide an extensive ablation study of the proposed method justifying the chosen configurations.
Original languageEnglish
StatePublished - 2020


  • Computer Science - Computer Vision and Pattern Recognition
  • Computer Science - Machine Learning
  • Statistics - Machine Learning


Dive into the research topics of 'Colored Noise Injection for Training Adversarially Robust Neural Networks'. Together they form a unique fingerprint.

Cite this