Add to ORKGPublic data has been frequently used to improve the privacy-accuracy trade-off of differentially private machine learning, but prior work largely assumes that this data come from the same distribution as the private. In this work, we look at how to use generic large-scale public data to improve the quality of differentially private image generation in Generative Adversarial Networks (GANs), and provide an improved method that uses public data effectively. Our method works under the assumption that the support of the public data distribution contains the support of the private; an example of this is when the public data come from a general-purpose internet-scale image source, while the private data consist of images of a specific type. Detai...
In this paper, we introduce a data augmentation-based defense strategy for preventing the reconstruc...
Machine Learning (ML) is accelerating progress across fields and industries, but relies on accessibl...
The performance of differentially private machine learning can be boosted significantly by leveragin...
Training even moderately-sized generative models with differentially-private stochastic gradient des...
Advances in computation have created high demand for large datasets, which in turn has sparked inter...
Generative Adversarial Networks (GANs) are a modern solution aiming to encourage public sharing of d...
Differentially private GANs have proven to be a promising approach for generating realistic syntheti...
Leveraging transfer learning has recently been shown to be an effective strategy for training large ...
We consider the problem of enhancing user privacy in common data analysis and machine learning devel...
Although machine learning models trained on massive data have led to break-throughs in several areas...
While modern machine learning models rely on increasingly large training datasets, data is often lim...
Differentially private data generation techniques have become a promising solution to the data priva...
In this paper, we propose generating artificial data that retain statistical properties of real data...
Today we are surrounded by IOT devices that constantly generate different kinds of data about its en...
Machine Learning (ML) has achieved enormous success in solving a variety of problems in computer vis...
In this paper, we introduce a data augmentation-based defense strategy for preventing the reconstruc...
Machine Learning (ML) is accelerating progress across fields and industries, but relies on accessibl...
The performance of differentially private machine learning can be boosted significantly by leveragin...
Training even moderately-sized generative models with differentially-private stochastic gradient des...
Advances in computation have created high demand for large datasets, which in turn has sparked inter...
Generative Adversarial Networks (GANs) are a modern solution aiming to encourage public sharing of d...
Differentially private GANs have proven to be a promising approach for generating realistic syntheti...
Leveraging transfer learning has recently been shown to be an effective strategy for training large ...
We consider the problem of enhancing user privacy in common data analysis and machine learning devel...
Although machine learning models trained on massive data have led to break-throughs in several areas...
While modern machine learning models rely on increasingly large training datasets, data is often lim...
Differentially private data generation techniques have become a promising solution to the data priva...
In this paper, we propose generating artificial data that retain statistical properties of real data...
Today we are surrounded by IOT devices that constantly generate different kinds of data about its en...
Machine Learning (ML) has achieved enormous success in solving a variety of problems in computer vis...
In this paper, we introduce a data augmentation-based defense strategy for preventing the reconstruc...
Machine Learning (ML) is accelerating progress across fields and industries, but relies on accessibl...
The performance of differentially private machine learning can be boosted significantly by leveragin...