Stealing attack against controlled information, along with the increasing number of
information leakage incidents, has become an emerging cyber security threat in recent …

Deep Learning has recently become hugely popular in machine learning for its ability to
solve end-to-end learning systems, in which the features and the classifiers are learned …

We quantitatively investigate how machine learning models leak information about the
individual data records on which they were trained. We focus on the basic membership …

Deep learning based on artificial neural networks is a very popular approach to modeling,
classifying, and recognizing complex data such as images, speech, and text. The …

Membership inference (MI) attacks exploit the fact that machine learning algorithms
sometimes leak information about their training data through the learned model. In this work …

Dropout is designed to relieve the overfitting problem in high-level vision tasks but is rarely
applied in low-level vision tasks, like image super-resolution (SR). As a classic regression …

Overfitting is one of the most critical challenges in deep neural networks, and there are
various types of regularization methods to improve generalization performance. Injecting …

Recently, training with adversarial examples, which are generated by adding a small but
worst-case perturbation on input examples, has improved the generalization performance of …

This paper considers the scenario that multiple data owners wish to apply a machine
learning method over the combined dataset of all owners to obtain the best possible …

Previous federated recommender systems are based on traditional matrix factorization,
which can improve personalized service but are vulnerable to gradient inference attacks …