Related papers: Minimax Filter: Learning to Preserve Privacy from …

Building a recommendation system involves analyzing user data, which can potentially leak sensitive information about users. Anonymizing user data is often not sufficient for preserving user privacy. Motivated by this, we propose a…

Differential privacy is a leading protection setting, focused by design on individual privacy. Many applications, in medical / pharmaceutical domains or social networks, rather posit privacy at a group level, a setting we call integral…

The design of a statistical signal processing privacy problem is studied where the private data is assumed to be observable. In this work, an agent observes useful data $Y$, which is correlated with private data $X$, and wants to disclose…

Fine-tuning adapts a pretrained machine learning model to a small, sensitive dataset, but this process risks memorizing individual new data points, making the model vulnerable to adversaries who seek to extract sensitive information. In…

Personal photos of individuals when shared online, apart from exhibiting a myriad of memorable details, also reveals a wide range of private information and potentially entails privacy risks (e.g., online harassment, tracking). To mitigate…

The approximation introduced by finite-precision representation of continuous data can induce arbitrarily large information leaks even when the computation using exact semantics is secure. Such leakage can thus undermine design efforts…

We present an optimization framework for solving multi-agent nonlinear programs subject to inequality constraints while keeping the agents' state trajectories private. Each agent has an objective function depending only upon its own state…

Privacy is under threat from artificial intelligence revolution fueled by unprecedented abundance of data. Differential privacy, an established candidate for privacy protection, is susceptible to adversarial attacks, acts conservatively,…

Federated learning facilitates the collaborative training of models without the sharing of raw data. However, recent attacks demonstrate that simply maintaining data locality during training processes does not provide sufficient privacy…

This paper studies how to apply differential privacy to constrained optimization problems whose inputs are sensitive. This task raises significant challenges since random perturbations of the input data often render the constrained…

Most methods for publishing data with privacy guarantees introduce randomness into datasets which reduces the utility of the published data. In this paper, we study the privacy-utility tradeoff by taking maximal leakage as the privacy…

Data privacy is an increasingly important aspect of many real-world Data sources that contain sensitive information may have immense potential which could be unlocked using the right privacy enhancing transformations, but current methods…

Differential privacy enables organizations to collect accurate aggregates over sensitive data with strong, rigorous guarantees on individuals' privacy. Previous work has found that under differential privacy, computing multiple correlated…

Differential Privacy (DP) is the current gold-standard for ensuring privacy for statistical queries. Estimation problems under DP constraints appearing in the literature have largely focused on providing equal privacy to all users. We…

Normalizing flow models have risen as a popular solution to the problem of density estimation, enabling high-quality synthetic data generation as well as exact probability density evaluation. However, in contexts where individuals are…

Although federated learning improves privacy of training data by exchanging local gradients or parameters rather than raw data, the adversary still can leverage local gradients and parameters to obtain local training data by launching…

Differential privacy (DP) offers a robust framework for safeguarding individual data privacy. To utilize DP in training modern machine learning models, differentially private optimizers have been widely used in recent years. A popular…

Distributed optimization and learning has recently garnered great attention due to its wide applications in sensor networks, smart grids, machine learning, and so forth. Despite rapid development, existing distributed optimization and…

The privacy-utility tradeoff problem is formulated as determining the privacy mechanism (random mapping) that minimizes the mutual information (a metric for privacy leakage) between the private features of the original dataset and a…

So far, privacy models follow two paradigms. The first paradigm, termed inferential privacy in this paper, focuses on the risk due to statistical inference of sensitive information about a target record from other records in the database.…