Learning Robustness at Test-Time from a Non-Robust Teacher

ArXi:2604.11590v1 Announce Type: new Nowadays, pretrained models are increasingly used as general-purpose backbones and adapted at test-time to downstream environments where target data are scarce and unlabeled. While this paradigm has proven effective for improving clean accuracy on the target domain, adversarial robustness has received far less attention, especially when the original pretrained model is not explicitly designed to be robust.