相关论文: Privacy Preserving Diffusion Models for Mixed-Type…

As one of the most successful generative models, diffusion models have demonstrated remarkable efficacy in synthesizing high-quality images. These models learn the underlying high-dimensional data distribution in an unsupervised manner.…

Federated Learning (FL) is a distributed machine learning paradigm based on protecting data privacy of devices, which however, can still be broken by gradient leakage attack via parameter inversion techniques. Differential privacy (DP)…

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…

Face recognition poses serious privacy risks due to its reliance on sensitive and immutable biometric data. While modern systems mitigate privacy risks by mapping facial images to embeddings (commonly regarded as privacy-preserving), model…

In the realm of multimedia data analysis, the extensive use of image datasets has escalated concerns over privacy protection within such data. Current research predominantly focuses on privacy protection either in data sharing or upon the…

Tabular data synthesis using diffusion models has gained significant attention for its potential to balance data utility and privacy. However, existing privacy evaluations often rely on heuristic metrics or weak membership inference attacks…

Matrix factorization (MF) mechanisms for differential privacy (DP) have substantially improved the state-of-the-art in privacy-utility-computation tradeoffs for ML applications in a variety of scenarios, but in both the centralized and…

Federated learning is a distributed learning technique that allows training a global model with the participation of different data owners without the need to share raw data. This architecture is orchestrated by a central server that…

Federated learning is distributed model training across several clients without disclosing raw data. Despite advancements in data privacy, risks still remain. Differential Privacy (DP) is a technique to protect sensitive data by adding…

Local differential privacy (LDP) has become a central topic in data privacy research, offering strong privacy guarantees by perturbing user data at the source and removing the need for a trusted curator. However, the noise introduced by LDP…

Training diffusion models on limited datasets poses challenges in terms of limited generation capacity and expressiveness, leading to unsatisfactory results in various downstream tasks utilizing pretrained diffusion models, such as domain…

Diffusion models are the leading approach for tabular data synthesis and are increasingly used to share sensitive records. Whether they actually protect privacy has become a pressing question. Membership inference attacks are the standard…

Federated learning (FL), as a type of collaborative machine learning framework, is capable of preserving private data from mobile terminals (MTs) while training the data into useful models. Nevertheless, from a viewpoint of information…

Machine learning (ML) models have been shown to leak private information from their training datasets. Differential Privacy (DP), typically implemented through the differential private stochastic gradient descent algorithm (DP-SGD), has…

Proper communication is key to the adoption and implementation of differential privacy (DP). However, a prior study found that laypeople did not understand the data perturbation processes of DP and how DP noise protects their sensitive…

Text-to-image generation for personalized identities aims at incorporating the specific identity into images using a text prompt and an identity image. Based on the powerful generative capabilities of DDPMs, many previous works adopt…

This paper introduces FairDP, a novel training mechanism designed to provide group fairness certification for the trained model's decisions, along with a differential privacy (DP) guarantee to protect training data. The key idea of FairDP…

Diffusion-based generative models have shown promise in synthesizing histopathology images to address data scarcity caused by privacy constraints. Diagnostic text reports provide high-level semantic descriptions, and masks offer…

The ability to train generative models that produce realistic, safe and useful tabular data is essential for data privacy, imputation, oversampling, explainability or simulation. However, generating tabular data is not straightforward due…

Nowadays, machine learning models and applications have become increasingly pervasive. With this rapid increase in the development and employment of machine learning models, a concern regarding privacy has risen. Thus, there is a legitimate…