Facebook open-sources differential privacy tool

Facebook’s Opacus is a library for training PyTorch models with differential privacy that’s ostensibly more scalable than existing state-of-the-art methods.

With the release of Opacus, Facebook says it hopes to provide an easier path for engineers to adopt differential privacy in AI and to accelerate in-the-field differential privacy research.

Typically, differential privacy entails injecting a small amount of noise into the raw data before feeding it into a local machine learning model, thus making it difficult for malicious actors to extract the original files from the trained model.

Source: Facebook open-sources Opacus, a PyTorch library for differential privacy | VentureBeat