相关论文: An Empirical Study on the Membership Inference Att…

Membership inference attack (MIA) has become one of the most widely used and effective methods for evaluating the privacy risks of machine learning models. These attacks aim to determine whether a specific sample is part of the model's…

Recent advancements in diffusion models have enabled high-fidelity and photorealistic image generation across diverse applications. However, these models also present security and privacy risks, including copyright violations, sensitive…

Generative AI technology has become increasingly integrated into our daily lives, offering powerful capabilities to enhance productivity. However, these same capabilities can be exploited by adversaries for malicious purposes. While…

Diffusion models have achieved remarkable progress in image generation, but their increasing deployment raises serious concerns about privacy. In particular, fine-tuned models are highly vulnerable, as they are often fine-tuned on small and…

Practitioners commonly download pretrained machine learning models from open repositories and finetune them to fit specific applications. We show that this practice introduces a new risk of privacy backdoors. By tampering with a pretrained…

With the rapid advancement of deep learning technology, pre-trained encoder models have demonstrated exceptional feature extraction capabilities, playing a pivotal role in the research and application of deep learning. However, their…

Over the last few years, federated learning (FL) has emerged as a prominent method in machine learning, emphasizing privacy preservation by allowing multiple clients to collaboratively build a model while keeping their training data…

We propose a new framework of synthesizing data using deep generative models in a differentially private manner. Within our framework, sensitive data are sanitized with rigorous privacy guarantees in a one-shot fashion, such that training…

Generating high-fidelity synthetic tabular data under formal differential privacy guarantees remains an open challenge. Methods that provide strong theoretical protection typically sacrifice the modeling of inter-feature dependencies…

Deep neural networks (DNNs) have recently been widely adopted in various applications, and such success is largely due to a combination of algorithmic breakthroughs, computation resource improvements, and access to a large amount of data.…

Synthetic data generators, when trained using privacy-preserving techniques like differential privacy, promise to produce synthetic data with formal privacy guarantees, facilitating the sharing of sensitive data. However, it is crucial to…

When synthetic data is released, some individuals are harder to protect than others. A patient with a rare disease combination or a transaction with unusual characteristics stands out from the crowd. Differential privacy provides worst-case…

Synthetic data has garnered attention as a Privacy Enhancing Technology (PET) in sectors such as healthcare and finance. When using synthetic data in practical applications, it is important to provide protection guarantees. In the…

Deep learning model developers often use cloud GPU resources to experiment with large data and models that need expensive setups. However, this practice raises privacy concerns. Adversaries may be interested in: 1) personally identifiable…

Federated Learning (FL) allows for the training of Machine Learning models in a collaborative manner without the need to share sensitive data. However, it remains vulnerable to Gradient Leakage Attacks (GLAs), which can reveal private…

Deep learning has attracted broad interest in healthcare and medical communities. However, there has been little research into the privacy issues created by deep networks trained for medical applications. Recently developed inference attack…

Generative AI systems are quickly improving, now able to produce believable output in several modalities including images, text, and audio. However, this fast development has prompted increased scrutiny concerning user privacy and the use…

Federated Distillation (FD) has emerged as a popular federated training framework, enabling clients to collaboratively train models without sharing private data. Public Dataset-Assisted Federated Distillation (PDA-FD), which leverages…

Generative Adversarial Networks (GANs) are typically trained to synthesize data, from images and more recently tabular data, under the assumption of directly accessible training data. Recently, federated learning (FL) is an emerging…

Graph Neural Networks (GNNs), which generalize traditional deep neural networks on graph data, have achieved state-of-the-art performance on several graph analytical tasks. We focus on how trained GNN models could leak information about the…