Related papers: Large-Scale Public Data Improves Differentially Pr…
We show that the canonical approach for training differentially private GANs -- updating the discriminator with differentially private stochastic gradient descent (DPSGD) -- can yield significantly improved results after modifications to…
Synthetic data generation, a cornerstone of Generative Artificial Intelligence, promotes a paradigm shift in data science by addressing data scarcity and privacy while enabling unprecedented performance. As synthetic data becomes more…
The need to analyze sensitive data, such as medical records or financial data, has created a critical research challenge in recent years. In this paper, we adopt the framework of differential privacy, and explore mechanisms for generating…
While cloud/sky image segmentation has extensive real-world applications, a large amount of labelled data is needed to train a highly accurate models to perform the task. Scarcity of such volumes of cloud/sky images with corresponding…
There are now several large scale deployments of differential privacy used to collect statistical information about users. However, these deployments periodically recollect the data and recompute the statistics using algorithms designed for…
Training of generative models especially Generative Adversarial Networks can easily diverge in low-data setting. To mitigate this issue, we propose a novel implicit data augmentation approach which facilitates stable training and synthesize…
When machine learning models are trained on synthetic data and then deployed on real data, there is often a performance drop due to the distribution shift between synthetic and real data. In this paper, we introduce a new ensemble strategy…
In this work, we develop a privacy-by-design generative model for synthesizing the activity diary of the travel population using state-of-art deep learning approaches. This proposed approach extends literature on population synthesis by…
Modern Generative Adversarial Networks are capable of creating artificial, photorealistic images from latent vectors living in a low-dimensional learned latent space. It has been shown that a wide range of images can be projected into this…
Tabular data synthesis has received wide attention in the literature. This is because available data is often limited, incomplete, or cannot be obtained easily, and data privacy is becoming increasingly important. In this work, we present a…
While deep neural networks have achieved remarkable success in various computer vision tasks, they often fail to generalize to new domains and subtle variations of input images. Several defenses have been proposed to improve the robustness…
Generative Adversarial Networks (GANs) have made releasing of synthetic images a viable approach to share data without releasing the original dataset. It has been shown that such synthetic data can be used for a variety of downstream tasks…
Transferring the knowledge of pretrained networks to new domains by means of finetuning is a widely used practice for applications based on discriminative models. To the best of our knowledge this practice has not been studied within the…
Privacy-preserving data publication, including synthetic data sharing, often experiences trade-offs between privacy and utility. Synthetic data is generally more effective than data anonymization in balancing this trade-off, however, not…
Differentially private training algorithms like DP-SGD protect sensitive training data by ensuring that trained models do not reveal private information. An alternative approach, which this paper studies, is to use a sensitive dataset to…
Diffusion models are becoming increasingly popular in synthetic data generation and image editing applications. However, these models can amplify existing biases and propagate them to downstream applications. Therefore, it is crucial to…
Broad adoption of machine learning techniques has increased privacy concerns for models trained on sensitive data such as medical records. Existing techniques for training differentially private (DP) models give rigorous privacy guarantees,…
Despite the growing availability of high-quality public datasets, the lack of training samples is still one of the main challenges of deep-learning for skin lesion analysis. Generative Adversarial Networks (GANs) appear as an enticing…
Generative adversarial networks (GANs) have shown great success in applications such as image generation and inpainting. However, they typically require large datasets, which are often not available, especially in the context of prediction…
The Generator of a Generative Adversarial Network (GAN) is trained to transform latent vectors drawn from a prior distribution into realistic looking photos. These latent vectors have been shown to encode information about the content of…