一句话：指出现有代码对抗攻击忽视自然性，并提出面向代码预训练模型的自然对抗攻击。
代码预训练模型已在许多重要软件工程任务中取得成功，但这些强大模型容易受到对抗攻击：对模型输入做微小扰动即可使受害模型产生错误输出。现有工作主要利用保持程序操作语义的样本攻击代码模型，却忽略了对抗样本生成的一项基本要求：扰动应对人类判断者而言是自然的，作者将其称为自然性要求。本文关注面向代码预训练模型的自然攻击，即对抗样本不仅应保持操作程序语义，还应满足人类感知上的自然性，从而提升攻击的隐蔽性与现实威胁。摘要未给出具体算法、评估基准和量化结果，因此方法细节与实验结论需参见全文。
Pre-trained models of code have achieved success in many important software engineering tasks. However, these powerful models are vulnerable to adversarial attacks that slightly perturb model inputs to make a victim model produce wrong outputs. Current works mainly attack models of code with examples that preserve operational program semantics but ignore a fundamental requirement for adversarial example generation: perturbations should be natural to human judges, which we refer to as naturalness requirement.