Attacks on Private Training Data

Attacks on Private Training Data

(Figure courtesy of Dr Ali Hatamizadeh, the author of GradViT) Recent studies have shown that training samples can be recovered from the corresponding gradients. This phenomenon is called Gradient Inversion (GradInv) attacks. The principle behind GradInv is to learn...
Green Computing Hub

Green Computing Hub

To foster collaboration and support the exchange of ideas and solutions on sustainable computing, we establish an international green computing hub.   In recent years, the energy consumption that is needed for computing processes has become an increasing concern....
Better Images of AI

Better Images of AI

Image source: Rens Dimmendaal & David Clode / Better Images of AI / Fish reversed / CC-BY 4.0 The content of this post is taken from: [Better Images of AI]   Did you observe that common images used in news stories and marketing material about AI are often...