REVIEW 1 cited by
On the security relevance of weights in deep learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
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.
Forward citations
Cited by 1 Pith paper
-
Universal Adversarial Audio Perturbations
Universal adversarial audio perturbations, found by a penalty-based optimizer, misclassify over 85% of test sounds across several 1D CNN audio classifiers, in both targeted and untargeted settings.
Discussion (0). Continue with ORCID to comment.