Adversarial attacks are a serious threat to the reliable deployment of machine learning models in safety-critical applications. They can misguide current models to predict incorrectly by slightly modifying the inputs. Recently, substantial work has shown that adversarial examples tend to deviate from the underlying data manifold of normal examples, whereas pre-trained masked language models can fit the manifold of normal NLP data. To explore how to use the masked language model in adversarial detection, we propose a novel textual adversarial example detection method, namely Masked Language Model-based Detection (MLMD), which can produce clearly distinguishable signals between normal examples and adversarial examples by exploring the changes in manifolds induced by the masked language model. MLMD features a plug and play usage (i.e., no need to retrain the victim model) for adversarial defense and it is agnostic to classification tasks, victim model's architectures, and to-be-defended attack methods. We evaluate MLMD on various benchmark textual datasets, widely studied machine learning models, and state-of-the-art (SOTA) adversarial attacks (in total $3*4*4 = 48$ settings). Experimental results show that MLMD can achieve strong performance, with detection accuracy up to 0.984, 0.967, and 0.901 on AG-NEWS, IMDB, and SST-2 datasets, respectively. Additionally, MLMD is superior, or at least comparable to, the SOTA detection defenses in detection accuracy and F1 score. Among many defenses based on the off-manifold assumption of adversarial examples, this work offers a new angle for capturing the manifold change. The code for this work is openly accessible at \url{https://github.com/mlmddetection/MLMDdetection}.

翻译：对抗性攻击对机器学习模型在安全关键型应用中的可靠部署构成严重威胁。攻击者通过轻微修改输入即可误导现有模型做出错误预测。近年来大量研究表明，对抗样本往往偏离正常样本的底层数据流形，而预训练掩码语言模型能够拟合自然语言处理数据的正常流形。为探索如何利用掩码语言模型进行对抗检测，我们提出了一种新颖的文本对抗样本检测方法——基于掩码语言模型的检测（MLMD），该方法通过探究掩码语言模型诱导的流形变化，可清晰区分正常样本与对抗样本的检测信号。MLMD具有即插即用的防御特性（即无需重新训练受害模型），且与分类任务、受害模型架构及待防御攻击方法无关。我们在多种基准文本数据集、广泛研究的机器学习模型及最新对抗攻击方法（共计3×4×4=48种设置）上评估了MLMD性能。实验结果表明，MLMD在AG-NEWS、IMDB和SST-2数据集上分别实现了0.984、0.967和0.901的检测准确率。此外，在检测准确率和F1分数方面，MLMD优于或至少持平于现有最优检测防御方法。本文从对抗样本偏离流形假设出发，为捕捉流形变化提供了全新视角。本工作代码已开源至\url{https://github.com/mlmddetection/MLMDdetection}。