The Victim and The Beneficiary: Exploiting a Poisoned Model to Train a Clean Model on Poisoned Data

ICCV 2023  ·  Zixuan Zhu, Rui Wang, Cong Zou, Lihua Jing ·

Recently, backdoor attacks have posed a serious security threat to the training process of deep neural networks (DNNs). The attacked model behaves normally on benign samples but outputs a specific result when the trigger is present. However, compared with the rocketing progress of backdoor attacks, existing defenses are difficult to deal with these threats effectively or require benign samples to work, which may be unavailable in real scenarios. In this paper, we find that the poisoned samples and benign samples can be distinguished with prediction entropy. This inspires us to propose a novel dual-network training framework: The Victim and The Beneficiary (V&B), which exploits a poisoned model to train a clean model without extra benign samples. Firstly, we sacrifice the Victim network to be a powerful poisoned sample detector by training on suspicious samples. Secondly, we train the Beneficiary network on the credible samples selected by the Victim to inhibit backdoor injection. Thirdly, a semi-supervised suppression strategy is adopted for erasing potential backdoors and improving model performance. Furthermore, to better inhibit missed poisoned samples, we propose a strong data augmentation method, AttentionMix, which works well with our proposed V&B framework. Extensive experiments on two widely used datasets against 6 state-of-the-art attacks demonstrate that our framework is effective in preventing backdoor injection and robust to various attacks while maintaining the performance on benign samples. Our code is available at https://github.com/Zixuan-Zhu/VaB.

PDF Abstract ICCV 2023 PDF ICCV 2023 Abstract

Datasets


  Add Datasets introduced or used in this paper

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods


No methods listed for this paper. Add relevant methods here