Machine learning (ML) models have been widely applied to various applications, including image classification, text generation, audio recognition, and graph data analysis. However …
Denoising diffusion probabilistic models are becoming the leading generative modeling paradigm for many important data modalities. Being the most prevalent in the computer …
The rapid advancement and widespread use of large language models (LLMs) have raised significant concerns regarding the potential leakage of personally identifiable information …
Recent work argues that robust training requires substantially larger datasets than those required for standard classification. On CIFAR-10 and CIFAR-100, this translates into a …
J Duan, F Kong, S Wang, X Shi… - … Conference on Machine …, 2023 - proceedings.mlr.press
Diffusion-based generative models have shown great potential for image synthesis, but there is a lack of research on the security and privacy risks they may pose. In this paper, we …
This explainer document aims to provide an overview of the current state of the rapidly expanding work on synthetic data technologies, with a particular focus on privacy. The …
Machine learning heavily relies on data, but real-world applications often encounter various data-related issues. These include data of poor quality, insufficient data points leading to …
Abstract Empirical attacks on Federated Learning (FL) systems indicate that FL is fraught with numerous attack surfaces throughout the FL execution. These attacks can not only …
Z Li, J Zhang, L Liu, J Liu - … of the IEEE/CVF Conference on …, 2022 - openaccess.thecvf.com
Federated Learning (FL) framework brings privacy benefits to distributed learning systems by allowing multiple clients to participate in a learning task under the coordination of a …