Factory Berlin partner, Google for Startups, cordially invites you to join the ‘Computing Private Statistics with Differential Privacy‘ codelab, which will be facilitated by Christiane Ahlheim, Data Scientist and Ehsaan Qadir, Customer Solutions Engineer.
In 2019 we open sourced our first Differential Privacy library to enable developers and organizations to learn from the majority of their data while simultaneously ensuring that those results do not allow any individual's data to be distinguished or re-identified.
In this codelab you will learn how to produce statistics that are preserving the user’s privacy by using differentially private aggregations.
Please register to codelab to keep you informed about the meeting details and logistics.
The codelab is suitable for developers, data scientists, business analysts, product managers who work with or analyze personable identifiable datasets to improve their product offerings or plan to publish statistics based on datasets that require a robust data anonymization technique to protect their user’s privacy and prevent data leakages.
Participants with some degree of familiarity with Go, the open source programming language, and Beam will have an easier time following the codelab and understanding the computational models, which will be using differentially private aggregations. There is no official technical experience requirement other than being able to read and write Go.
We recommend reading up on the topic of data anonymization, as the process of aggregating data across multiple users to protect user privacy, and differential privacy as a strong privacy notion of anonymization. In addition, we recommend reading the Beam introduction to familiarize yourself with a high-level library for writing data-processing pipelines. In case you want to code along during the introduction of the codelab, we recommend having this page ready.