Search Results for author:
Found 5 papers, 2 papers with code
Friendly Sharpness-Aware Minimization
By decomposing the adversarial perturbation in SAM into full gradient and stochastic gradient noise components, we discover that relying solely on the full gradient component degrades generalization while excluding it leads to improved performance.
Machine Unlearning by Suppressing Sample Contribution
Machine Unlearning (MU) is to forget data from a well-trained model, which is practically important due to the "right to be forgotten".
Low-Dimensional Gradient Helps Out-of-Distribution Detection
To bridge this gap, in this paper, we conduct a comprehensive investigation into leveraging the entirety of gradient information for OOD detection.
Self-Ensemble Protection: Training Checkpoints Are Good Data Protectors
In this paper, we uncover them by model checkpoints' gradients, forming the proposed self-ensemble protection (SEP), which is very effective because (1) learning on examples ignored during normal training tends to yield DNNs ignoring normal examples; (2) checkpoints' cross-model gradients are close to orthogonal, meaning that they are as diverse as DNNs with different architectures.
FG-UAP: Feature-Gathering Universal Adversarial Perturbation
Deep Neural Networks (DNNs) are susceptible to elaborately designed perturbations, whether such perturbations are dependent or independent of images.
