Abstract
Despite great success on many machine learning tasks, deep neural networks are still vulnerable to adversarial samples. While gradient-based adversarial attack methods are well-explored in the field of computer vision, it is impractical to directly apply them in natural language processing due to the discrete nature of text. To bridge this gap, we propose a general framework to adapt existing gradient-based methods to craft textual adversarial samples. In this framework, gradient-based continuous perturbations are added to the embedding layer and are amplified in the forward propagation process. Then the final perturbed latent representations are decoded with a mask language model head to obtain potential adversarial samples. In this paper, we instantiate our framework with \textbf{T}extual \textbf{P}rojected \textbf{G}radient \textbf{D}escent (\textbf{TPGD}). We conduct comprehensive experiments to evaluate our framework by performing transfer black-box attacks on BERT, RoBERTa and ALBERT on three benchmark datasets. Experimental results demonstrate our method achieves an overall better performance and produces more fluent and grammatical adversarial samples compared to strong baseline methods. All the code and data will be made public.
Abstract (translated)
URL
https://arxiv.org/abs/2110.15317
