Most ReLU Networks Suffer from ℓ^2 Adversarial Perturbations

10/28/2020
by   Amit Daniely, et al.
0

We consider ReLU networks with random weights, in which the dimension decreases at each layer. We show that for most such networks, most examples x admit an adversarial perturbation at an Euclidean distance of O(x/√(d)), where d is the input dimension. Moreover, this perturbation can be found via gradient flow, as well as gradient descent with sufficiently small steps. This result can be seen as an explanation to the abundance of adversarial examples, and to the fact that they are found via gradient descent.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset