Enhancing Model Robustness By Incorporating Adversarial Knowledge Into Semantic Representation

Despite that deep neural networks (DNNs) have achieved enormous success in many domains like NLP, they have also been proven to be vulnerable to maliciously generated adversarial examples. Such inherent vulnerability has threatened various real-world deployed DNNs-based applications. To strength the model robustness, several countermeasures have been proposed in the English NLP domain and obtained satisfactory performance. However, due to the unique language properties of Chinese, it is not trivial to extend existing defenses to the Chinese domain. Therefore, we propose AdvGraph, a novel defense which enhances the robustness of Chinese-based NLP models by incorporating adversarial knowledge into the semantic representation of the input. Extensive experiments on two real-world tasks show that AdvGraph exhibits better performance compared with previous work: (i) effective - it significantly strengthens the model robustness even under the adaptive attacks setting without negative impact on model performance over legitimate input; (ii) generic - its key component, i.e., the representation of connotative adversarial knowledge is task-agnostic, which can be reused in any Chinese-based NLP models without retraining; and (iii) efficient - it is a light-weight defense with sub-linear computational complexity, which can guarantee the efficiency required in practical scenarios.