Search Results for author:
Found 2 papers, 1 papers with code
DHBE: Data-free Holistic Backdoor Erasing in Deep Neural Networks via Restricted Adversarial Distillation
Instead of the staged pipeline, the DHBE treats the backdoor erasing task as a unified adversarial procedure, which seeks equilibrium between two different competing processes: distillation and backdoor regularization.
Joint learning of interpretation and distillation
The extra trust brought by the model interpretation has made it an indispensable part of machine learning systems.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
