"Unlearning Backdoor Attacks through Gradient-Based Model Pruning."

Kealan Dunnett et al. (2024)

Details and statistics

DOI: 10.48550/ARXIV.2405.03918

access: open

type: Informal or Other Publication

metadata version: 2024-06-07

a service of  Schloss Dagstuhl - Leibniz Center for Informatics