Search Results for author:
Found 3 papers, 0 papers with code
Finding Dynamics Preserving Adversarial Winning Tickets
Modern deep neural networks (DNNs) are vulnerable to adversarial attacks and adversarial training has been shown to be a promising method for improving the adversarial robustness of DNNs.
Linear Model Against Malicious Adversaries with Local Differential Privacy
Secure collaborative learning is significantly difficult with the presence of malicious adversaries who may deviates from the secure protocol.
Understanding and Quantifying Adversarial Examples Existence in Linear Classification
We show that linear classifiers can be made robust to strong adversarial examples attack in cases where no adversarial robust linear classifiers exist under the previous definition.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
