A little-known algorithmic process called “differential privacy” helps keep census data anonymous. Conservatives want it gone.

The U.S. Department of Commerce has completely banned noise infusion (a core method of differential privacy) in statistical products from the Census Bureau and the Bureau of Economic Analysis. This ar

Every analytics tool makes you a promise. I built one where the promise is unnecessary, because the math makes individual visits unknowable.

Since 2016, Apple has claimed that device analytics collected to improve user experience are protected by differential privacy (DP). Apple's DifferentialPrivacy framework is deployed across its operating systems and handles sensitive signals such as Safari domains, keyboard events, photo attributes, and health-related reports. Because Apple has not open-sourced its privatization algorithms, these privacy claims have been difficult to verify independently. We present a client-side audit of Apple's DP framework on macOS Sonoma 14.2 and Sequoia 15.6. We reverse engineer the shipped binaries, recover Objective-C interfaces, build runtime harnesses that execute Apple's deployed mechanisms, and test whether their outputs match the advertised privacy guarantees. Our audit covers nearly all active deployed mechanisms, including Count Median Sketch, Hadamard-CMS, randomized-response mechanisms, and Prio-style secure aggregation. We find multiple implementation bugs and misconfigurations. Every audited mechanism that relies on floating-point noise fails to meet its advertised DP or zero-knowledge proof guarantee, due to insecure samplers with known floating-point vulnerabilities. We also find secure-aggregation configurations with local DP disabled, exposing pre-aggregation records to any party with access to those logs. Overall, we find DP violations in 5 of 9 audited mechanisms, affecting 87% of data collection in macOS Sonoma and 68% in Sequoia. We also identify public leaked iPhone logs that can be decoded to recover private information, including Safari domains and keyboard emoji signals.

Differential privacy is defined in terms of pairs of neighboring datasets. That is, \(M\) is \((\varepsilon,\delta)\)-differentially private if, for all measurable events \(T\) and all neighboring pai...

June 2–3, 2026 in Boston...

When training artificial intelligence systems, developers need to use privacy-enhancing technologies to ensure that the subjects of the training data are not exposed, new study suggests.

At the Eyes-Off Data Summit and the 2025 OpenDP Community Meeting, we and collaborators announced the launch of the Differential Privacy Deployments Registry—a public-facing repository of real-world…