Related papers: Programming Frameworks for Differential Privacy
In modern settings of data analysis, we may be running our algorithms on datasets that are sensitive in nature. However, classical machine learning and statistical algorithms were not designed with these risks in mind, and it has been…
Some organizations use software applications to manage their customers' personal, medical, or financial information. In the United States, those software applications are obligated to preserve users' privacy and to comply with the United…
Large language models (LLMs) have emerged as powerful tools for tackling complex tasks across diverse domains, but they also raise privacy concerns when fine-tuned on sensitive data due to potential memorization. While differential privacy…
Differential privacy provides a theoretical framework for processing a dataset about $n$ users, in a way that the output reveals a minimal information about any single user. Such notion of privacy is usually ensured by noise-adding…
We revisit benchmarks for differentially private image classification. We suggest a comprehensive set of benchmarks, allowing researchers to evaluate techniques for differentially private machine learning in a variety of settings, including…
The authors discuss their experience applying differential privacy with a complex data set with the goal of enabling standard approaches to statistical data analysis. They highlight lessons learned and roadblocks encountered, distilling…
The growing proliferation of distributed information systems, allows organizations to offer their business processes to a worldwide audience through Web services. Semantic Web services have emerged as a means to achieve the vision of…
Differential Privacy (DP) provides strong guarantees on the risk of compromising a user's data in statistical learning applications, though these strong protections make learning challenging and may be too stringent for some use cases. To…
We develop formal privacy mechanisms for releasing statistics from data with many outlying values, such as income data. These mechanisms ensure that a per-record differential privacy guarantee degrades slowly in the protected records'…
Differential privacy has emerged as an significant cornerstone in the realm of scientific hypothesis testing utilizing confidential data. In reporting scientific discoveries, Bayesian tests are widely adopted since they effectively…
How to achieve differential privacy in the distributed setting, where the dataset is distributed among the distrustful parties, is an important problem. We consider in what condition can a protocol inherit the differential privacy property…
Integrating Foundation Models (FMs) into recommendation systems is an emerging and promising research direction. However, centralized paradigms face growing pressure from privacy concerns and strict regulatory requirements. Federated…
Cloud computing enables users to process and store data remotely on high-performance computers and servers by sharing data over the Internet. However, transferring data to clouds causes unavoidable privacy concerns. Here, we present a…
Differential privacy is a mathematical framework for privacy-preserving data analysis. Changing the hyperparameters of a differentially private algorithm allows one to trade off privacy and utility in a principled way. Quantifying this…
Imagine a group of citizens willing to collectively contribute their personal data for the common good to produce socially useful information, resulting from data analytics or machine learning computations. Sharing raw personal data with a…
As data-driven technologies advance swiftly, maintaining strong privacy measures becomes progressively difficult. Conventional $(\epsilon, \delta)$-differential privacy, while prevalent, exhibits limited adaptability for many applications.…
Research software has been categorized in different contexts to serve different goals. We start with a look at what research software is, before we discuss the purpose of research software categories. We propose a multi-dimensional…
The need for a privacy management layer in today's systems started to manifest with the emergence of new systems for privacy-preserving analytics and privacy compliance. As a result, many independent efforts have emerged that try to provide…
Data-driven agriculture, which integrates technology and data into agricultural practices, has the potential to improve crop yield, disease resilience, and long-term soil health. However, privacy concerns, such as adverse pricing,…
Data splitting preserves privacy by partitioning data into various fragments to be stored remotely and shared. It supports most data operations because data can be stored in clear as opposed to methods that rely on cryptography. However,…