Enforcing Linearity in DNN Succours Robustness and Adversarial Image Generation

Sarkar, Anindya and Iyengar, Raghu (2020) Enforcing Linearity in DNN Succours Robustness and Adversarial Image Generation. In: 29th International Conference on Artificial Neural Networks, ICANN 2020, 15 September 2020through 18 September 2020, Bratislava.

Full text not available from this repository. (Request a copy)

Abstract

Recent studies on the adversarial vulnerability of neural networks have shown that models trained with the objective of minimizing an upper bound on the worst-case loss over all possible adversarial perturbations improve robustness against adversarial attacks. Beside exploiting adversarial training framework, we show that by enforcing a Deep Neural Network (DNN) to be linear in transformed input and feature space improves robustness significantly. We also demonstrate that by augmenting the objective function with Local Lipschitz regularizer boost robustness of the model further. Our method outperforms most sophisticated adversarial training methods and achieves state of the art adversarial accuracy on MNIST, CIFAR10 and SVHN dataset. We also propose a novel adversarial image generation method by leveraging Inverse Representation Learning and Linearity aspect of an adversarially trained deep neural network classifier. © 2020, Springer Nature Switzerland AG.

[error in script]

IITH Creators: