RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models
arXiv:2110.07831
Abstract
Backdoor attacks, which maliciously control a well-trained model's outputs of the instances with specific triggers, are recently shown to be serious threats to the safety of reusing deep neural networks (DNNs). In this work, we propose an efficient online defense mechanism based on robustness-aware perturbations. Specifically, by analyzing the backdoor training process, we point out that there exists a big gap of robustness between poisoned and clean samples. Motivated by this observation, we construct a word-based robustness-aware perturbation to distinguish poisoned samples from clean samples to defend against the backdoor attacks on natural language processing (NLP) models. Moreover, we give a theoretical analysis about the feasibility of our robustness-aware perturbation-based defense method. Experimental results on sentiment analysis and toxic detection tasks show that our method achieves better defending performance and much lower computational costs than existing online defense methods. Our code is available at https://github.com/lancopku/RAP.
EMNLP 2021 (main conference), long paper, camera-ready version
References in corpus (4)
- Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
- Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks
- Can Adversarial Weight Perturbations Inject Neural Backdoors?
- Design and Evaluation of a Multi-Domain Trojan Detection Method on Deep Neural Networks