A Method for Computing Class-wise Universal Adversarial Perturbations

Understand

We present an algorithm for computing class-specific universal adversarial perturbations for deep neural networks.

• Such perturbations can induce misclassification in a large fraction of images of a specific class.
• Unlike previous methods that use iterative optimization for computing a universal perturbation, the proposed method employs a perturbation that is a linear function of weights of the neural network and hence can be computed much faster.
• The method does not require any training data and has no hyper-parameters.