RIBAC: Towards Robust and Imperceptible Backdoor Attack against Compact DNN

Abstract

In this paper, we propose to study and develop Robust and Imperceptible Backdoor Attack against Compact DNN models (RIBAC). By performing systematic analysis and exploration on the important design knobs, we propose a framework that can learn the proper trigger patterns, model parameters and pruning masks in an efficient way. Thereby achieving high trigger stealthiness, high attack success rate and high model efficiency simultaneously.

Publication
In European Conference on Computer Vision 2022