Flooding-X: Improving BERT's Resistance to Adversarial Attacks via Loss-Restricted Fine-TuningDownload PDF

Anonymous

Nov 16, 2021 (edited Jan 14, 2022)ACL ARR 2021 November Blind SubmissionReaders: Everyone
  • Abstract: Adversarial robustness has attracted much attention recently, and the mainstream solution is adversarial training. However, the tradition of generating adversarial perturbations for each input embedding (in the settings of NLP) scales up the training computational complexity by the number of gradient steps it takes to obtain the adversarial samples. To address this problem, we leverage Flooding method which primarily aims at better generalization and we find promising in defending adversarial attacks. We further propose an effective criterion to bring hyper-parameter-dependent flooding into effect with a narrowed-down search space by measuring how the gradient steps taken within one epoch affect the loss of each batch. Our approach requires zero adversarial sample for training, and its time consumption is equivalent to fine-tuning, which can be 2-15 times faster than standard adversarial training. We experimentally show that our method improves Bert's resistance to textual adversarial attacks by a large margin, and achieves state-of-the-art robust accuracy on various text classification and GLUE tasks.
0 Replies

Loading