Differentially private synthetic data is a promising alternative for
sen...
Recent studies show that private training data can be leaked through the...
Deep neural networks have developed rapidly and have achieved outstandin...
Studying the sensitivity of weight perturbation in neural networks and i...
Adversarial examples causing evasive predictions are widely used to eval...
Adversarial robustness has become an emerging challenge for neural netwo...
Recent studies have found that deep learning systems are vulnerable to
a...