Learning to Ignore Adversarial Attacks
Despite the strong performance of current NLP models, they can be brittle against adversarial attacks. To enable effective learning against adversarial inputs, we introduce the use of rationale models that can explicitly learn to ignore attack tokens. We find that the rationale models can ignore over 90\% of attack tokens. This approach leads to consistent sizable improvements ($\sim$8\%) over baseline models in robustness, for both BERT and RoBERTa, on MultiRC and FEVER, and also reliably outperforms data augmentation with adversarial examples alone. In many cases, we find that our method is able to close the gap between model performance on a clean test set and an attacked test set, eliminating the effect of adversarial attacks.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Learning to Ignore Adversarial Attacks
Despite the strong performance of current NLP models, they can be brittle against adversarial attacks. To enable effective learning against adversarial inputs, we introduce the use of rationale models that can explicitly…
Data AugmentationAttention for Adversarial Attacks: Learning from your Mistakes
In order to apply Neural Networks in safety-critical settings, such as healthcare or autonomous driving, we need to be able to analyse their robustness against adversarial attacks. As complete verification is often compu…
Autonomous DrivingSmoothness Analysis of Adversarial Training
Deep neural networks are vulnerable to adversarial attacks. Recent studies about adversarial robustness focus on the loss landscape in the parameter space since it is related to optimization and generalization performanc…
Adversarial RobustnessDoes Adversarial Robustness Really Imply Backdoor Vulnerability?
Recent research has revealed a trade-off between the robustness against adversarial attacks and backdoor attacks. Specifically, with the increasing adversarial robustness obtained through adversarial training, the model …
Adversarial RobustnessState-of-the-art optical-based physical adversarial attacks for deep learning computer vision systems
Adversarial attacks can mislead deep learning models to make false predictions by implanting small perturbations to the original input that are imperceptible to the human eye, which poses a huge security threat to the co…
Adversarial Attack