Related papers: Synthetic Data Outliers: Navigating Identity Discl…

This paper proposes and compares measures of identity and attribute disclosure risk for synthetic data. Data custodians can use the methods proposed here to inform the decision as to whether to release synthetic versions of confidential…

Data for good implies unfettered access to data. But data owners must be conservative about how, when, and why they share data or risk violating the trust of the people they aim to help, losing their funding, or breaking the law. Data…

Privacy is an increasingly important aspect of data publishing. Reasoning about privacy, however, is fraught with pitfalls. One of the most significant is the auxiliary information (also called external knowledge, background knowledge, or…

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…

We investigate whether Differentially Private SGD offers better privacy in practice than what is guaranteed by its state-of-the-art analysis. We do so via novel data poisoning attacks, which we show correspond to realistic privacy attacks.…

The deployment of facial recognition systems has created an ethical dilemma: achieving high accuracy requires massive datasets of real faces collected without consent, leading to dataset retractions and potential legal liabilities under…

Synthetic data is increasingly used to support research without exposing sensitive user content. Social media data is one of the types of datasets that would hugely benefit from representative synthetic equivalents that can be used to…

Synthetic data generators, when trained using privacy-preserving techniques like differential privacy, promise to produce synthetic data with formal privacy guarantees, facilitating the sharing of sensitive data. However, it is crucial to…

Diferentially private (DP) synthetic datasets are a powerful approach for training machine learning models while respecting the privacy of individual data providers. The effect of DP on the fairness of the resulting trained models is not…

Commercial companies that collect user data on a large scale have been the main beneficiaries of this trend since the success of deep learning techniques is directly proportional to the amount of data available for training. Massive data…

Practitioners commonly download pretrained machine learning models from open repositories and finetune them to fit specific applications. We show that this practice introduces a new risk of privacy backdoors. By tampering with a pretrained…

Sharing health and behavioral data raises significant privacy concerns, as conventional de-identification methods are susceptible to privacy attacks. Differential Privacy (DP) provides formal guarantees against re-identification risks, but…

Differentially private data generation techniques have become a promising solution to the data privacy challenge -- it enables sharing of data while complying with rigorous privacy guarantees, which is essential for scientific progress in…

Today's deep models are often unable to detect inputs which do not belong to the training distribution. This gives rise to confident incorrect predictions which could lead to devastating consequences in many important application fields…

There is a need for synthetic training and test datasets that replicate statistical distributions of original datasets without compromising their confidentiality. A lot of research has been done in leveraging Generative Adversarial Networks…

Synthetic data is an increasingly popular tool for training deep learning models, especially in computer vision but also in other areas. In this work, we attempt to provide a comprehensive survey of the various directions in the development…

The synthetic data approach to data confidentiality has been actively researched on, and for the past decade or so, a good number of high quality work on developing innovative synthesizers, creating appropriate utility measures and risk…

Generating synthetic data, with or without differential privacy, has attracted significant attention as a potential solution to the dilemma between making data easily available, and the privacy of data subjects. Several works have shown…

The switch from a Model-Centric to a Data-Centric mindset is putting emphasis on data and its quality rather than algorithms, bringing forward new challenges. In particular, the sensitive nature of the information in highly regulated…

Machine learning has the potential to assist many communities in using the large datasets that are becoming more and more available. Unfortunately, much of that potential is not being realized because it would require sharing data in a way…