WaNet – Imperceptible Warping-based Backdoor Attack

WaNet – Imperceptible Warping-based Backdoor Attack

Authors: Anh Tuan Nguyen, Anh Tuan Tran

ICLR 2021

AbstractPDFBibtex

With the thriving of deep learning and the widespread practice of using pre-trained networks, backdoor attacks have become an increasing security threat drawing many research interests in recent years. A third-party model can be poisoned in training to work well in normal conditions but behave maliciously when a trigger pattern appears. However, the existing backdoor attacks are all built on noise perturbation triggers, making them noticeable to humans. In this paper, we instead propose using warping-based triggers. The proposed backdoor outperforms the previous methods in a human inspection test by a wide margin, proving its stealthiness. To make such models undetectable by machine defenders, we propose a novel training mode, called the “noise mode. The trained networks successfully attack and bypass the state-ofthe art defense methods on standard classification datasets, including MNIST, CIFAR-10, GTSRB, and CelebA. Behavior analyses show that our backdoors are transparent to network inspection, further proving this novel attack mechanism’s efficiency.

@inproceedings{
nguyen2021wanet,
title={WaNet - Imperceptible Warping-based Backdoor Attack},
author={Tuan Anh Nguyen and Anh Tuan Tran},
booktitle={International Conference on Learning Representations},
year={2021},
url={https://openreview.net/forum?id=eEn8KTtJOx}
}