Search Results for author:
Found 2 papers, 0 papers with code
CV4Code: Sourcecode Understanding via Visual Code Representations
We present CV4Code, a compact and effective computer vision method for sourcecode understanding.
Enhancing Privacy against Inversion Attacks in Federated Learning by using Mixing Gradients Strategies
We show that otherwise it is possible to directly recover all vectors in a mini-batch without any numerical optimisation due to the de-mixing nature of the cross entropy loss.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
