相关论文: Application-driven Privacy-preserving Data Publish…

Ensuring differential privacy of models learned from sensitive user data is an important goal that has been studied extensively in recent years. It is now known that for some basic learning problems, especially those involving…

Data privacy has emerged as an important issue as data-driven deep learning has been an essential component of modern machine learning systems. For instance, there could be a potential privacy risk of machine learning systems via the model…

Generative Adversarial Networks (GANs) are deep learning architectures capable of generating synthetic datasets. Despite producing high-quality synthetic images, the default GAN has no control over the kinds of images it generates. The…

Classical techniques for protecting facial image privacy typically fall into two categories: data-poisoning methods, exemplified by Fawkes, which introduce subtle perturbations to images, or anonymization methods that generate images…

Federated clustering (FC) is an essential extension of centralized clustering designed for the federated setting, wherein the challenge lies in constructing a global similarity measure without the need to share private data. Conventional…

The proliferation of big data has brought an urgent demand for privacy-preserving data publishing. Traditional solutions to this demand have limitations on effectively balancing the tradeoff between privacy and utility of the released data.…

Generative adversarial nets (GANs) have been widely studied during the recent development of deep learning and unsupervised learning. With an adversarial training mechanism, GAN manages to train a generative model to fit the underlying…

This paper aims to improve privacy-preserving visual recognition, an increasingly demanded feature in smart camera applications, by formulating a unique adversarial training framework. The proposed framework explicitly learns a degradation…

Generative Adversarial Networks (GANs) and diffusion models have emerged as leading approaches for high-quality image synthesis. While both can be trained under differential privacy (DP) to protect sensitive data, their sensitivity to…

Conditional Generative Adversarial Networks (CGANs) exhibit significant potential in supervised learning model training by virtue of their ability to generate realistic labeled images. However, numerous studies have indicated the privacy…

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…

The wide-spread availability of rich data has fueled the growth of machine learning applications in numerous domains. However, growth in domains with highly-sensitive data (e.g., medical) is largely hindered as the private nature of data…

We introduce the DP-auto-GAN framework for synthetic data generation, which combines the low dimensional representation of autoencoders with the flexibility of Generative Adversarial Networks (GANs). This framework can be used to take in…

Machine learned models trained on organizational communication data, such as emails in an enterprise, carry unique risks of breaching confidentiality, even if the model is intended only for internal use. This work shows how confidentiality…

Machine learning tools are becoming increasingly powerful and widely used. Unfortunately membership attacks, which seek to uncover information from data sets used in machine learning, have the potential to limit data sharing. In this paper…

Despite the remarkable success of Generative Adversarial Networks (GANs) on text, images, and videos, generating high-quality tabular data is still under development owing to some unique challenges such as capturing dependencies in…

We present heuristics for solving the maximin problem induced by the generative adversarial privacy setting for linear and convolutional neural network (CNN) adversaries. In the linear adversary setting, we present a greedy algorithm for…

Data privacy has become an increasingly important issue in Machine Learning (ML), where many approaches have been developed to tackle this challenge, e.g. cryptography (Homomorphic Encryption (HE), Differential Privacy (DP), etc.) and…

The ability of machines to comprehend and produce language that is similar to that of humans has revolutionized sectors like customer service, healthcare, and finance thanks to the quick advances in Natural Language Processing (NLP), which…

The rise of generative artificial intelligence (AI) has facilitated automated product design but often neglects valuable consumer preference data within companies' internal datasets. Additionally, external sources such as social media and…