Leveraging Diffusion-Based Image Variations for Robust Training on Poisoned Data. (arXiv:2310.06372v2 [cs.CR] UPDATED)

Backdoor attacks pose a serious security threat for training neural networks
as they surreptitiously introduce hidden functionalities into a model. Such
backdoors remain silent during inference on clean inputs, evading detection due
to inconspicuous behavior. However, once a specific trigger pattern appears in
the input data, the backdoor activates, causing the model to execute its
concealed function. Detecting such poisoned samples within vast datasets is
virtually impossible through manual inspection. To address this challenge, we
propose a novel approach that …

attacks backdoor backdoor attacks backdoors data detection hidden image input inputs networks neural networks security security threat serious serious security silent threat training trigger