Can Backdoor Attacks Survive Time-Varying Models?. (arXiv:2206.04677v1 [cs.CR])

Backdoors are powerful attacks against deep neural networks (DNNs). By
poisoning training data, attackers can inject hidden rules (backdoors) into
DNNs, which only activate on inputs containing attack-specific triggers. While
existing work has studied backdoor attacks on a variety of DNN models, they
only consider static models, which remain unchanged after initial deployment.

In this paper, we study the impact of backdoor attacks on a more realistic
scenario of time-varying DNN models, where model weights are updated
periodically to handle …

attacks backdoor