In this paper, we propose a new privacy solution for the data used to train a recommender
system, ie, the user–item matrix. The user–item matrix contains implicit information, which …

We address the problem of maximizing privacy of stochastic dynamical systems whose state
information is released through quantized sensor data. In particular, we consider the setting …

Robust machine learning formulations have emerged to address the prevalent vulnerability
of deep neural networks to adversarial examples. Our work draws the connection between …

The problem of data privacy-protecting sensitive or personal data from discovery-has been a
long-standing research issue. In this regard, differential privacy, introduced in 2006, is …

In standard supervised learning, we assume that we are trying to learn some target variable
𝑌 from some data 𝑋. However, many learning problems can be framed as supervised …

We consider data release protocols for data X=(S,U), where S is sensitive; the released data
Y contains as much information about X as possible, measured as I(X;Y), without leaking too …

This paper considers the problem of publishing data X while protecting the correlated
sensitive information S. We propose a linear method to generate the sanitized data Y with …

Online social networks enable users to participate in different activities, such as connecting
with each other and sharing different contents online. These activities lead to the generation …

Adversarial examples have recently exposed the severe vulnerability of neural network
models. However, most of the existing attacks require some form of target model information …

The access frequency pattern leakage reveals sensitive information over encrypted cloud
data, such as query inclinations and interests. Even worse, adversaries can infer the content …