The Gretel Epoch #3
Welcome back to The Gretel Epoch, your source for privacy engineering insights, product updates, educational content, upcoming events, and community news from Gretel.
Here’s what’s new this month:
Case Study: Generating Synthetic Time-Series Data for One of the Largest Financial Institutions in the World
This POC deep dive covers how Gretel generated high-quality synthetic time-series data for one of the largest global financial institutions in the world, and the methods we designed to assess the accuracy and privacy of our models and data. Developers can test our methods by opening up our example Colab Notebook, clicking “Run All”, and entering your API key to run the entire experiment, or by following along with the 3-step process outlined in the post!
Upcoming Gretel Demo & AMA with Weights & Biases Developer Community!
Next Tuesday, January 25, Gretel has the honor of speaking with the active community of MLOps practitioners building with Weights & Biases tools. Gretel’s co-founder and CPO, Alex Watson, will join host, Sanyam Bhutani, to demo our SDK, discuss some recent case studies, and answer questions in an AMA round with the audience. You can register for the free event here. Please retweet the news and get your networks to join the conversation, too!
Gretel Presenting at TROPT Data Privacy Week 2022
Next Wednesday, January 26, Gretel’s Senior Applied Scientist, Lipika Ramaswamy, will be presenting a talk titled “Solving Privacy Problems with Synthetic Data” at The Rise of Privacy Tech’s Data Privacy Week 2022. If you’re interested in the future of privacy tech, join us and hundreds of other privacy and security engineers, CPOs, GRC folks, builders, and innovators. Some limited free tickets are still available.
Gretel’s Advanced Data Privacy Filters & ML Accuracy
A look at how using Gretel’s Privacy Filters to immunize synthetic datasets against adversarial attacks can impact machine learning accuracy. This is the culmination of a lot of work our research team has done on the nature of adversarial attacks.
New Article in Towards Data Science on Creating a Location Generator GAN
In TDS this post, we train a FastCUT GAN on public location data from a few cities to predict realistic locations across the world. You can follow along and replicate this work from the GitHub repo link we have included in the post.
New Video Series — Setting Up Your Gretel Environment
Just getting started with privacy engineering? Try this 4-part video series on setting up your Gretel environment! In 20 mins, you can be programming privacy like a pro. 🦾
That’s it for this week! Cheers, Team Gretel
Gretel pioneered Privacy Engineering as a Service and a toolkit for synthetic data that features easy-to-use APIs and an open-source AI-based core, built for developers. We help you make safe, shareable data so you can innovate and create value faster.