Related papers: Differentially Private Generative Adversarial Netw…
Differentially-Private SGD (DP-SGD) and its adaptive variant DP-Adam are powerful techniques to protect user privacy when using sensitive data to train neural networks. During training, converting model weights and activations into…
Graph Neural Networks (GNNs) are a popular technique for modelling graph-structured data and computing node-level representations via aggregation of information from the neighborhood of each node. However, this aggregation implies an…
Machine learning (ML) models used in medical imaging diagnostics can be vulnerable to a variety of privacy attacks, including membership inference attacks, that lead to violations of regulations governing the use of medical data and…
This paper studies how to learn variational autoencoders with a variety of divergences under differential privacy constraints. We often build a VAE with an appropriate prior distribution to describe the desired properties of the learned…
Training deep learning models with differential privacy (DP) results in a degradation of performance. The training dynamics of models with DP show a significant difference from standard training, whereas understanding the geometric…
Generative Adversarial Networks (GANs) are a revolutionary class of Deep Neural Networks (DNNs) that have been successfully used to generate realistic images, music, text, and other data. However, GAN training presents many challenges,…
Imagine training a machine learning model with Differentially Private Stochastic Gradient Descent (DP-SGD), only to discover post-training that the noise level was either too high, crippling your model's utility, or too low, compromising…
Diffusion models are becoming defector generative models, which generate exceptionally high-resolution image data. Training effective diffusion models require massive real data, which is privately owned by distributed parties. Each data…
Deep learning models are often trained on datasets that contain sensitive information such as individuals' shopping transactions, personal contacts, and medical records. An increasingly important line of work therefore has sought to train…
Differential privacy (DP) has become the standard for private data analysis. Certain machine learning applications only require privacy protection for specific protected attributes. Using naive variants of differential privacy in such use…
Privacy preservation in machine learning, particularly through Differentially Private Stochastic Gradient Descent (DP-SGD), is critical for sensitive data analysis. However, existing statistical inference methods for SGD predominantly focus…
Graph Neural Networks (GNNs) have established themselves as the state-of-the-art models for many machine learning applications such as the analysis of social networks, protein interactions and molecules. Several among these datasets contain…
Traditional data masking techniques such as anonymization cannot achieve the expected privacy protection while ensuring data utility for privacy-preserving machine learning. Synthetic data plays an increasingly important role as it…
This paper studies model-inversion attacks, in which the access to a model is abused to infer information about the training data. Since its first introduction, such attacks have raised serious concerns given that training data usually…
Deep learning models are known to put the privacy of their training data at risk, which poses challenges for their safe and ethical release to the public. Differentially private stochastic gradient descent is the de facto standard for…
We consider three different variants of differential privacy (DP), namely approximate DP, R\'enyi DP (RDP), and hypothesis test DP. In the first part, we develop a machinery for optimally relating approximate DP to RDP based on the joint…
The increased application of machine learning (ML) in sensitive domains requires protecting the training data through privacy frameworks, such as differential privacy (DP). DP requires to specify a uniform privacy level $\varepsilon$ that…
In spite that Federated Learning (FL) is well known for its privacy protection when training machine learning models among distributed clients collaboratively, recent studies have pointed out that the naive FL is susceptible to gradient…
Differentially private (DP) training preserves the data privacy usually at the cost of slower convergence (and thus lower accuracy), as well as more severe mis-calibration than its non-private counterpart. To analyze the convergence of DP…
We investigate the construction of gradient-guided conditional diffusion models for reconstructing private images, focusing on the adversarial interplay between differential privacy noise and the denoising capabilities of diffusion models.…