Test-Time Adaptation for Backdoor Defense. (arXiv:2308.06107v1 [cs.CR])

Deep neural networks have played a crucial part in many critical domains,
such as autonomous driving, face recognition, and medical diagnosis. However,
deep neural networks are facing security threats from backdoor attacks and can
be manipulated into attacker-decided behaviors by the backdoor attacker. To
defend the backdoor, prior research has focused on using clean data to remove
backdoor attacks before model deployment. In this paper, we investigate the
possibility of defending against backdoor attacks at test time by utilizing
partially …

attacks autonomous autonomous driving backdoor backdoor attacks critical defense diagnosis domains driving face recognition facing medical networks neural networks recognition research security security threats test threats