Search Results for author:
Found 2 papers, 2 papers with code
Efficient Backdoor Removal Through Natural Gradient Fine-tuning
Extensive experiments show that the proposed method achieves state-of-the-art performance on a wide range of backdoor defense benchmarks: four different datasets- CIFAR10, GTSRB, Tiny-ImageNet, and ImageNet; 13 recent backdoor attacks, e. g.
SSDA: Secure Source-Free Domain Adaptation
Source-free domain adaptation (SFDA) is a popular unsupervised domain adaptation method where a pre-trained model from a source domain is adapted to a target domain without accessing any source data.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
