Malicious server (MS) attacks have enabled the scaling of data stealing ...
Reliable neural networks (NNs) provide important inference-time reliabil...
Fair representation learning (FRL) is a popular class of methods aiming ...
State-of-the-art neural network verifiers are fundamentally based on one...
Recent work shows that sensitive user data can be reconstructed from gra...
We study the problem of adversarially robust self-supervised learning on...
Certified defenses based on convex relaxations are an established techni...
Recent advances in representation learning on graphs, mainly leveraging ...