Revisiting Data-Free Knowledge Distillation with Poisoned Teachers

Junyuan Hong

Yi Zeng

Shuyang Yu*

Lingjuan Lyu

Ruoxi Jia*

Jiayu Zhou*

* External authors

ICML 2023

2023

Abstract

Data-free knowledge distillation (KD) helps realistically transfer knowledge from a pre-trained model (known as the teacher model) to a smaller model (known as the student model) without access to the original training data used for training the teacher model. However, the security of the synthetic or out-of-distribution (OOD) data required in data-free KD is largely unknown and under-explored. In this work, we make the first effort to uncover the security risk of data-free KD w.r.t. untrusted pre-trained models. We then propose ABD, the first plug-in defensive method for data-free KD methods to mitigate the chance of potential backdoors being transferred. We empirically evaluate the effectiveness of our proposed ABD in diminishing transferred backdoor knowledge while maintaining compatible downstream performances as the vanilla KD. We envision this work as a milestone for alarming and mitigating the potential backdoors in data-free KD.