# Differential Privacy Published articles for Differential Privacy. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Fully Homomorphic Encryption in Production Systems DevFeed: [Fully Homomorphic Encryption in Production Systems]() Original publisher: [Read original article]() Published: 2024-07-31T07:00:00Z Content type: article Language: en Sources: [Jeremy Kun]() Topics: [homomorphic encryption](), [FHE](), [Encryption](), [Cryptography](), [Edge](), [Microsoft](), [iOS](), [Differential Privacy](), [Embeddings](), [clustering](), [Library]() Tags: [apple](), [clustering](), [cryptography](), [differential-privacy](), [embeddings](), [encryption](), [fhe](), [homomorphic-encryption](), [ios](), [library](), [mathematics](), [microsoft-edge](), [programming](), [systems]() ### AI overview A living document catalogs production systems known to use fully or somewhat homomorphic encryption. It describes deployments and techniques involving Microsoft Edge password checking, Apple's Live Caller ID Lookup, and Apple's private image search, while distinguishing FHE from SHE. ### Source excerpt In this living document, I will list all production systems I'm aware of that use fully homomorphic encryption (FHE). For background on FHE, see my overview of the field. If you have any information about production FHE systems not in this list, or corrections to information in this list, please send me an email with sufficient detail allow the claim to be publicly verified. For all production deployments, I will distinguish between cases where the deployed system does "fully" homomorphic encryption (with bootstrapping), aka FHE, and "somewhat" homomorphic encryption, aka SHE (avoiding bootstrapping). ## Advances in private training for production on-device language models DevFeed: [Advances in private training for production on-device language models]() Original publisher: [Read original article]() Author: Google AI (noreply@blogger.com) Published: 2024-02-21T20:15:00Z Content type: article Language: en Sources: [Google Research]() Topics: [Language models](), [Federated Learning](), [Google](), [Mobile]() Tags: [differential-privacy](), [federated-learning](), [gboard](), [google](), [language-models](), [on-device](), [on-device-learning](), [phones](), [privacy](), [production](), [research](), [responsible-ai](), [training]() ### AI overview This Google Research article describes advances in privately training Gboard's on-device language models. It explains how federated learning keeps training data on users' devices while differential privacy provides formal privacy guarantees. The article reports that all Gboard next-word-prediction neural language models use federated learning with formal differential privacy guarantees, across more than 30 models, 7 or more languages, and 15 or more countries. ### Source excerpt Posted by Zheng Xu, Research Scientist, and Yanxiang Zhang, Software Engineer, Google Language models (LMs) trained to predict the next word given input text are the key technology for many applications [1, 2]. In Gboard, LMs are used to improve users' typing experience by supporting features like next word prediction (NWP), Smart Compose, smart completion and suggestion, slide to type, and proofread. Deploying models on users' devices rather than enterprise servers has advantages like lower latency and better privacy for model usage. While training on-device models directly from user data effectively improves the utility performance for applications such as NWP and smart text selection, protecting the privacy of user data for model training is important. Gboard features powered by on-device language models. In this blog we discuss how years of research advances now power the private training of Gboard LMs, since the proof-of-concept development of federated learning (FL) in 2017 and formal differential privacy (DP) guarantees in 2022. FL enables mobile phones to collaboratively learn a model while keeping all the training data on device, and DP provides a quantifiable measure of data anonymization. Formally, DP is often characterized by (ε, δ) with smaller values representing stronger guarantees. Machine learning (ML) models are considered to have reasonable DP guarantees for ε=10 and strong DP guarantees for ε=1 when δ is small. As of today, all NWP neural network LMs in Gboard are trained with FL with formal DP guarantees, and all future launches of Gboard LMs trained on user data require DP. These 30+ Gboard on-device LMs are launched in 7+ languages and 15+ countries, and satisfy (ɛ, δ)-DP guarantees of small δ of 10-10 and ɛ between 0.994 and 13.69. To the best of our knowledge, this is the largest known deployment of user-level DP in production at Google or anywhere, and the first time a strong DP guarantee of ɛ < 1 is announced for models trained directly on ## DP-Auditorium: A flexible library for auditing differential privacy DevFeed: [DP-Auditorium: A flexible library for auditing differential privacy]() Original publisher: [Read original article]() Author: Google AI (noreply@blogger.com) Published: 2024-02-13T22:11:00Z Content type: article Language: en Sources: [Google Research]() Topics: [Library](), [Testing](), [Open Source](), [Python](), [Tool]() Tags: [algorithms](), [data-protection](), [differential-privacy](), [library](), [open-source](), [privacy](), [python](), [research](), [responsible-ai](), [security-and-privacy](), [testing]() ### AI overview Google Research introduces DP-Auditorium, an open source Python library that audits differential privacy guarantees using black-box access to mechanisms. It includes testing algorithms for Rényi, pure, and approximate differential privacy and can identify guarantee violations and suggest suitable tests for particular bugs. ### Source excerpt Posted by Mónica Ribero Díaz, Research Scientist, Google Research Differential privacy (DP) is a property of randomized mechanisms that limit the influence of any individual user's information while processing and analyzing data. DP offers a robust solution to address growing concerns about data protection, enabling technologies across industries and government applications (e.g., the US census) without compromising individual user identities. As its adoption increases, it's important to identify the potential risks of developing mechanisms with faulty implementations. Researchers have recently found errors in the mathematical proofs of private mechanisms, and their implementations. For example, researchers compared six sparse vector technique (SVT) variations and found that only two of the six actually met the asserted privacy guarantee. Even when mathematical proofs are correct, the code implementing the mechanism is vulnerable to human error. However, practical and efficient DP auditing is challenging primarily due to the inherent randomness of the mechanisms and the probabilistic nature of the tested guarantees. In addition, a range of guarantee types exist, (e.g., pure DP, approximate DP, Rényi DP, and concentrated DP), and this diversity contributes to the complexity of formulating the auditing problem. Further, debugging mathematical proofs and code bases is an intractable task given the volume of proposed mechanisms. While ad hoc testing techniques exist under specific assumptions of mechanisms, few efforts have been made to develop an extensible tool for testing DP mechanisms. To that end, in "DP-Auditorium: A Large Scale Library for Auditing Differential Privacy", we introduce an open source library for auditing DP guarantees with only black-box access to a mechanism (i.e., without any knowledge of the mechanism's internal properties). DP-Auditorium is implemented in Python and provides a flexible interface that allows contributions to continuously improve ## "Practical Math" Preview: Collect Sensitive Survey Responses Privately DevFeed: ["Practical Math" Preview: Collect Sensitive Survey Responses Privately]() Original publisher: [Read original article]() Published: 2022-05-14T09:40:49Z Content type: tutorial Language: en Sources: [Jeremy Kun]() Topics: [math](), [Statistics](), [Code](), [Software]() Tags: [bias](), [code](), [collect](), [differential-privacy](), [mathematics](), [politics](), [practical](), [practical-math](), [privacy](), [programming](), [python](), [random](), [randomized-algorithm](), [research](), [responses](), [survey]() ### AI overview This chapter preview explains randomized response, a survey technique for estimating aggregate statistics about sensitive questions while preserving respondents' privacy. Respondents use private coin flips to introduce randomization and maintain plausible deniability. ### Source excerpt This is a draft of a chapter from my in-progress book, Practical Math for Programmers: A Tour of Mathematics in Production Software. Tip: Determine an aggregate statistic about a sensitive question, when survey respondents do not trust that their responses will be kept secret. Solution: import random def respond_privately(true_answer: bool) -> bool: '''Respond to a survey with plausible deniability about your answer.''' be_honest = random.random() < 0.5 random_answer = random.random() < 0. ## Why Theoretical Computer Scientists Aren't Worried About Privacy DevFeed: [Why Theoretical Computer Scientists Aren't Worried About Privacy]() Original publisher: [Read original article]() Published: 2013-06-10T09:51:27Z Content type: opinion Language: en Sources: [Jeremy Kun]() Topics: [online privacy](), [Security](), [national security](), [Computer science](), [Google](), [backdoor](), [Statistics](), [Databases](), [Users]() Tags: [backdoor](), [computer-science](), [cryptography](), [databases](), [differential-privacy](), [google](), [homomorphic-encryption](), [national-security](), [politics](), [privacy](), [security](), [statistics](), [users]() ### AI overview This opinion article discusses public concern about government surveillance and privacy, arguing that privacy, convenience, and security can be maintained together technologically. It also distinguishes the author's personal privacy preferences from opposition to privacy violations as policy. ### Source excerpt There has been a lot of news recently on government surveillance of its citizens. The biggest two that have pervaded my news feeds are the protests in Turkey, which in particular have resulted in particular oppression of social media users, and the recent light on the US National Security Agency's widespread "backdoor" in industry databases at Google, Verizon, Facebook, and others. It appears that the facts are in flux, as some companies have denied their involvement in this program, but regardless of the truth the eye of the public has landed firmly on questions of privacy.