Search Results for author:
Found 2 papers, 0 papers with code
Fine-Tuning with Differential Privacy Necessitates an Additional Hyperparameter Search
For instance, we achieve 77. 9% accuracy for $(\varepsilon, \delta)=(2, 10^{-5})$ on CIFAR-100 for a model pretrained on ImageNet.
Dataset Inference for Self-Supervised Models
We introduce a new dataset inference defense, which uses the private training set of the victim encoder model to attribute its ownership in the event of stealing.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
