works on
adversarial machine learning 1backdoor attacks 1clean-label 1image classification 1machine unlearning 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

cs.CR2026

Benign on Label, Malicious by Design: Clean-Label Dormant-to-Activated Backdoor via Machine Unlearning with Removable Camouflage

Dongdong Zhao, Can Li, Xiang Yao +3

The paper proposes a clean‑label backdoor attack that stays dormant during training and becomes active only after specific camouflage samples are removed via machine unlearning, us…