Google open sources video-blurring tool Magritte

(Reuters file image)

Search giant Google has said it has open-sourced two of its privacy-enhancing technologies-Magritte and Fully Homomorphic Encryption (FHE) Transpiler.

Project Magritte is a machine-learning tool that can detect objects and blur them whenever they are seen. It can be useful in sensitive situations such as hiding someone's licence plate or protecting someone's identity during a live interview.

"This code is especially useful for video journalists who want to provide increased privacy assurances," Google said in a blog post.

"By using this open-source code, videographers can save time in blurring objects from a video, while knowing that the underlying ML algorithm can perform detection across a video with high accuracy."

FHE Transpiler allows developers to perform computations on encrypted data without revealing the information to them.

Google said that advancements in Transpiler allow the tool to perform with low-computational costs. It is also faster.

"As more aspects of our daily lives continue to become digitized, the technology industry’s responsibility to keep personal data safe grows," said Google.

"PETs ensure Google can provide great experiences like helping you find a restaurant’s most popular dishes or getting better recommendations as you type a message, all while keeping our users’ information anonymous and protected."