Backdoor Defense via Suppressing Model Shortcuts. (arXiv:2211.05631v1 [cs.CV])

Recent studies have demonstrated that deep neural networks (DNNs) are
vulnerable to backdoor attacks during the training process. Specifically, the
adversaries intend to embed hidden backdoors in DNNs so that malicious model
predictions can be activated through pre-defined trigger patterns. In this
paper, we explore the backdoor mechanism from the angle of the model structure.
We select the skip connection for discussions, inspired by the understanding
that it helps the learning of model `shortcuts' where backdoor triggers are
usually easier …

backdoor defense