论文标题
评估胸部X射线分类的对抗性鲁棒性：陷阱和最佳实践
On Evaluating Adversarial Robustness of Chest X-ray Classification: Pitfalls and Best Practices
论文作者
论文摘要
对抗性攻击的脆弱性是深度神经网络的众所周知的弱点。尽管大多数研究都集中在具有标准化基准等标准化基准（例如ImageNet和Cifar）的自然图像上，但很少的研究尤其是在医疗领域中考虑了现实世界的应用。我们的研究表明，与以前的主张相反，胸部X射线分类的鲁棒性更难评估，并根据数据集，架构和鲁棒性指标进行非常不同的评估。我们认为，以前的研究并未考虑医学诊断的特殊性，例如疾病的共同发生，标记者的分歧（领域专家），攻击的威胁模型以及对每种成功攻击的风险影响。 在本文中，我们讨论了方法论基础，回顾陷阱和最佳实践，并提出了用于评估胸部X射线分类模型鲁棒性的新方法学考虑因素。我们对3个数据集，7种模型和18种疾病的评估是对胸部X射线分类模型鲁棒性的最大评估。
Vulnerability to adversarial attacks is a well-known weakness of Deep Neural Networks. While most of the studies focus on natural images with standardized benchmarks like ImageNet and CIFAR, little research has considered real world applications, in particular in the medical domain. Our research shows that, contrary to previous claims, robustness of chest x-ray classification is much harder to evaluate and leads to very different assessments based on the dataset, the architecture and robustness metric. We argue that previous studies did not take into account the peculiarity of medical diagnosis, like the co-occurrence of diseases, the disagreement of labellers (domain experts), the threat model of the attacks and the risk implications for each successful attack. In this paper, we discuss the methodological foundations, review the pitfalls and best practices, and suggest new methodological considerations for evaluating the robustness of chest xray classification models. Our evaluation on 3 datasets, 7 models, and 18 diseases is the largest evaluation of robustness of chest x-ray classification models.
