Recent developments in deep learning have led to great success in various natural
language processing (NLP) tasks. However, these applications may involve data that …

Data augmentation techniques, such as simple image transformations and combinations,
are highly effective at improving the generalization of computer vision models, especially …

We initiate a formal study on the concept of learnable obfuscation and aim to answer the
following question: is there a type of data encoding that maintains the" learnability" of …

This paper focuses on the problem of Differentially Private Stochastic Optimization for (multi-
layer) fully connected neural networks with a single output node. In the first part, we examine …

We study the fundamental problem of the construction of optimal randomization in
Differential Privacy (DP). Depending on the clipping strategy or additional properties of the …

Federated learning (FL) enables distributed clients to collaboratively train a machine
learning model without sharing raw data with each other. However, it suffers from the …

Provable privacy typically requires involved analysis and is often associated with
unacceptable accuracy loss. While many empirical verification or approximation methods …

Differentially private stochastic gradient descent (DP-SGD) is known to have poorer training
and test performance on large neural networks, compared to ordinary stochastic gradient …

Deep learning with differential privacy (DP) has garnered significant attention over the past
years, leading to the development of numerous methods aimed at enhancing model …

Federated learning (FL) faces two primary challenges: the risk of privacy leakage due to
parameter sharing and communication inefficiencies. To address these challenges, we …