相关论文: Preserving Privacy in GANs Against Membership Infe…

The primary promise of decentralized learning is to allow users to engage in the training of machine learning models in a collaborative manner while keeping their data on their premises and without relying on any central entity. However,…

Generative Adversarial Networks (GANs) have brought about rapid progress towards generating photorealistic images. Yet the equitable allocation of their modeling capacity among subgroups has received less attention, which could lead to…

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.…

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…

Due to confidentiality issues, it can be difficult to access or share interesting datasets for methodological development in actuarial science, or other fields where personal data are important. We show how to design three different types…

With the proliferation of Artificial Intelligence, there has been a massive increase in the amount of data required to be accumulated and disseminated digitally. As the data are available online in digital landscapes with complex and…

Previous studies have developed fairness methods for biased models that exhibit discriminatory behaviors towards specific subgroups. While these models have shown promise in achieving fair predictions, recent research has identified their…

Large language models (LLMs) have become the backbone of modern natural language processing but pose privacy concerns about leaking sensitive training data. Membership inference attacks (MIAs), which aim to infer whether a sample is…

Insufficient training data is a major bottleneck for most deep learning practices, not least in medical imaging where data is difficult to collect and publicly available datasets are scarce due to ethics and privacy. This work investigates…

While Generative Adversarial Networks (GANs) are fundamental to many generative modelling applications, they suffer from numerous issues. In this work, we propose a principled framework to simultaneously mitigate two fundamental issues in…

We study the privacy implications of training recurrent neural networks (RNNs) with sensitive training datasets. Considering membership inference attacks (MIAs), which aim to infer whether or not specific data records have been used in…

Training generative adversarial networks (GAN) using too little data typically leads to discriminator overfitting, causing training to diverge. We propose an adaptive discriminator augmentation mechanism that significantly stabilizes…

Generative Adversarial Networks (GANs) have gained momentum for their ability to model image distributions. They learn to emulate the training set and that enables sampling from that domain and using the knowledge learned for useful…

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…

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…

Leveraging the power of deep learning to design nanophotonic devices has been an area of active research in recent times, with Generative Adversarial Networks (GANs) being a popular choice alongside autoencoder-based methods. However, both…

The proliferation of smart, connected, always listening devices have introduced significant privacy risks to users in a smart home environment. Beyond the notable risk of eavesdropping, intruders can adopt machine learning techniques to…

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…

One of the biggest issues facing the use of machine learning in medical imaging is the lack of availability of large, labelled datasets. The annotation of medical images is not only expensive and time consuming but also highly dependent on…

Images posted online present a privacy concern in that they may be used as reference examples for a facial recognition system. Such abuse of images is in violation of privacy rights but is difficult to counter. It is well established that…