On the security relevance of weights in deep learning

Kathrin Grosse, Thomas A. Trost, Marius Mosbach, Michael Backes, Dietrich Klakow

Recently, a weight-based attack on stochastic gradient descent inducing overfitting has been proposed. We show that the threat is broader: A task-independent permutation on the initial weights suffices to limit the achieved accuracy to for example 50% on the Fashion MNIST dataset from initially more than $90$%. These findings are confirmed on MNIST and CIFAR. We formally confirm that the attack succeeds with high likelihood and does not depend on the data. Empirically, weight statistics and loss appear unsuspicious, making it hard to detect the attack if the user is not aware. Our paper is thus a call for action to acknowledge the importance of the initial weights in deep learning.

Knowledge Graph

arrow_drop_up

Comments

Sign up or login to leave a comment