Moderate-fitting as a natural backdoor defender for pre-trained language models
Advances in Neural Information Processing Systems, 2022•proceedings.neurips.cc
Despite the great success of pre-trained language models (PLMs) in a large set of natural
language processing (NLP) tasks, there has been a growing concern about their security in
real-world applications. Backdoor attack, which poisons a small number of training samples
by inserting backdoor triggers, is a typical threat to security. Trained on the poisoned
dataset, a victim model would perform normally on benign samples but predict the attacker-
chosen label on samples containing pre-defined triggers. The vulnerability of PLMs under …
language processing (NLP) tasks, there has been a growing concern about their security in
real-world applications. Backdoor attack, which poisons a small number of training samples
by inserting backdoor triggers, is a typical threat to security. Trained on the poisoned
dataset, a victim model would perform normally on benign samples but predict the attacker-
chosen label on samples containing pre-defined triggers. The vulnerability of PLMs under …
Abstract
Despite the great success of pre-trained language models (PLMs) in a large set of natural language processing (NLP) tasks, there has been a growing concern about their security in real-world applications. Backdoor attack, which poisons a small number of training samples by inserting backdoor triggers, is a typical threat to security. Trained on the poisoned dataset, a victim model would perform normally on benign samples but predict the attacker-chosen label on samples containing pre-defined triggers. The vulnerability of PLMs under backdoor attacks has been proved with increasing evidence in the literature. In this paper, we present several simple yet effective training strategies that could effectively defend against such attacks. To the best of our knowledge, this is the first work to explore the possibility of backdoor-free adaptation for PLMs. Our motivation is based on the observation that, when trained on the poisoned dataset, the PLM's adaptation follows a strict order of two stages:(1) a moderate-fitting stage, where the model mainly learns the major features corresponding to the original task instead of subsidiary features of backdoor triggers, and (2) an overfitting stage, where both features are learned adequately. Therefore, if we could properly restrict the PLM's adaptation to the moderate-fitting stage, the model would neglect the backdoor triggers but still achieve satisfying performance on the original task. To this end, we design three methods to defend against backdoor attacks by reducing the model capacity, training epochs, and learning rate, respectively. Experimental results demonstrate the effectiveness of our methods in defending against several representative NLP backdoor attacks. We also perform visualization-based analysis to attain a deeper understanding of how the model learns different features, and explore the effect of the poisoning ratio. Finally, we explore whether our methods could defend against backdoor attacks for the pre-trained CV model. The codes are publicly available at https://github. com/thunlp/Moderate-fitting.
proceedings.neurips.cc