Related papers: Differentially Private Generative Adversarial Netw…
In this paper, we present a simple approach to train Generative Adversarial Networks (GANs) in order to avoid a \textit {mode collapse} issue. Implicit models such as GANs tend to generate better samples compared to explicit models that are…
As deep learning technologies advance, increasingly more data is necessary to generate general and robust models for various tasks. In the medical domain, however, large-scale and multi-parties data training and analyses are infeasible due…
Open data plays a fundamental role in the 21th century by stimulating economic growth and by enabling more transparent and inclusive societies. However, it is always difficult to create new high-quality datasets with the required privacy…
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…
Machine learning has been applied to almost all fields of computer science over the past decades. The introduction of GANs allowed for new possibilities in fields of medical research and text prediction. However, these new fields work with…
Despite the successes in capturing continuous distributions, the application of generative adversarial networks (GANs) to discrete settings, like natural language tasks, is rather restricted. The fundamental reason is the difficulty of…
A major challenge for machine learning is increasing the availability of data while respecting the privacy of individuals. Here we combine the provable privacy guarantees of the differential privacy framework with the flexibility of…
Deep learning techniques based on neural networks have shown significant success in a wide range of AI tasks. Large-scale training datasets are one of the critical factors for their success. However, when the training datasets are…
Deep generative models have gained much attention given their ability to generate data for applications as varied as healthcare to financial technology to surveillance, and many more - the most popular models being generative adversarial…
Distributed learning such as federated learning or collaborative learning enables model training on decentralized data from users and only collects local gradients, where data is processed close to its sources for data privacy. The nature…
Ubiquitous anomalies endanger the security of our system constantly. They may bring irreversible damages to the system and cause leakage of privacy. Thus, it is of vital importance to promptly detect these anomalies. Traditional supervised…
Limited data access is a longstanding barrier to data-driven research and development in the networked systems community. In this work, we explore if and how generative adversarial networks (GANs) can be used to incentivize data sharing by…
Generative Adversarial Networks (GANs) are a powerful class of generative models in the deep learning community. Current practice on large-scale GAN training utilizes large models and distributed large-batch training strategies, and is…
Existing deep learning technologies generally learn the features of chest X-ray data generated by Generative Adversarial Networks (GAN) to diagnose COVID-19 pneumonia. However, the above methods have a critical challenge: data privacy. GAN…
Generative adversarial network (GAN) has gotten wide re-search interest in the field of deep learning. Variations of GAN have achieved competitive results on specific tasks. However, the stability of training and diversity of generated…
We study the problem of learning representations that are private yet informative, i.e., provide information about intended "ally" targets while hiding sensitive "adversary" attributes. We propose Exclusion-Inclusion Generative Adversarial…
Graph Neural Networks (GNNs) are a popular technique for modelling graph-structured data and computing node-level representations via aggregation of information from the neighborhood of each node. However, this aggregation implies an…
Training Generative Adversarial Networks (GANs) remains a challenging problem. The discriminator trains the generator by learning the distribution of real/generated data. However, the distribution of generated data changes throughout the…
Recent advances in computing have allowed for the possibility to collect large amounts of data on personal activities and private living spaces. To address the privacy concerns of users in this environment, we propose a novel framework…
We consider the problem of generating private synthetic versions of real-world graphs containing private information while maintaining the utility of generated graphs. Differential privacy is a gold standard for data privacy, and the…