Related papers: Statistical Learning Theory Approach for Data Clas…

Objective: To enable privacy-preserving learning of high quality generative and discriminative machine learning models from distributed electronic health records. Methods and Results: We describe general and scalable strategy to build…

The rise of connected personal devices together with privacy concerns call for machine learning algorithms capable of leveraging the data of a large number of agents to learn personalized models under strong privacy requirements. In this…

Learning a classifier from private data collected by multiple parties is an important problem that has many potential applications. How can we build an accurate and differentially private global classifier by combining locally-trained…

Personalized health analytics increasingly rely on population benchmarks to provide contextual insights such as ''How do I compare to others like me?'' However, cohort-based aggregation of health data introduces nontrivial privacy risks,…

Storage-efficient privacy-preserving learning is crucial due to increasing amounts of sensitive user data required for modern learning tasks. We propose a framework for reducing the storage cost of user data while at the same time providing…

We explore the training of generative adversarial networks with differential privacy to anonymize image data sets. On MNIST, we numerically measure the privacy-utility trade-off using parameters from $\epsilon$-$\delta$ differential privacy…

Attacks that aim to identify the training data of public neural networks represent a severe threat to the privacy of individuals participating in the training data set. A possible protection is offered by anonymization of the training data…

Synthetic data has recently reached a level of visual fidelity that makes it nearly indistinguishable from real data, offering great promise for privacy-preserving data sharing in medical imaging. However, fully synthetic datasets still…

Fine-tuning large language models (LLMs) with local data is a widely adopted approach for organizations seeking to adapt LLMs to their specific domains. Given the shared characteristics in data across different organizations, the idea of…

In this work, we focus on protection against identity disclosure in the publication of sparse multidimensional data. Existing multidimensional anonymization techniquesa) protect the privacy of users either by altering the set of…

Machine learning is increasingly used in the most diverse applications and domains, whether in healthcare, to predict pathologies, or in the financial sector to detect fraud. One of the linchpins for efficiency and accuracy in machine…

In statistical disclosure control, the goal of data analysis is twofold: The released information must provide accurate and useful statistics about the underlying population of interest, while minimizing the potential for an individual…

Web query log data contain information useful to research; however, release of such data can re-identify the search engine users issuing the queries. These privacy concerns go far beyond removing explicitly identifying information such as…

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…

Companies that have an online presence-in particular, companies that are exclusively digital-often subscribe to this business model: collect data from the user base, then expose the data to advertisement agencies in order to turn a profit.…

When applying differential privacy to sensitive data, we can often improve performance using external information such as other sensitive data, public data, or human priors. We propose to use the learning-augmented algorithms (or algorithms…

Differential privacy (DP) allows the quantification of privacy loss when the data of individuals is subjected to algorithmic processing such as machine learning, as well as the provision of objective privacy guarantees. However, while…

We investigate omni-supervised learning, a special regime of semi-supervised learning in which the learner exploits all available labeled data plus internet-scale sources of unlabeled data. Omni-supervised learning is lower-bounded by…

Researchers find weaknesses in current strategies for protecting privacy in large datasets. Many anonymized datasets are reidentifiable, and norms for offering data subjects notice and consent over emphasize individual responsibility. Based…

In recent years, with the continuous development of significant data industrialization, trajectory data have more and more critical analytical value for urban construction and environmental monitoring. However, the trajectory contains a lot…