Tag
This paper proposes a training-time backdoor defense called Trapping and Removing (TR), which introduces a lightweight shortcut branch as a honeypot to trap backdoor knowledge and then discards it, enhanced by a knowledge decoupling strategy with entropy-based weight assignment.
This paper studies distillation attacks where model outputs can enable imitation, proposing a minimax game framework and a forward-pass-only defense called Product-of-Experts, showing that adaptive students recover more capability than passive evaluation suggests.