Google announced a new module for machine-learning framework TensorFlow to allow developers to safeguard user data with “differential privacy,” The Verge reports. TensorFlow Privacy effectively makes it so that artificial intelligence models trained on user data become unable to encode personally identifiable information. “If we don’t get something like differential privacy into TensorFlow, then we just know it won’t be as easy for teams inside and outside of Google to make use of it,” Google Product Manager Carey Radebaugh explained. “So for us it’s important to get it into TensorFlow, to open source it, and to start to create this community around it.”
If you want to comment on this post, you need to login.