SegPGD：一种用于评估和提升分割鲁棒性的有效且高效的对抗攻击
SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustness
AI总结：
本文提出高效分割对抗攻击 SegPGD，并通过收敛性分析证明其在相同迭代次数下优于 PGD，同时将其用于对抗训练以提升分割模型鲁棒性。
摘要：
基于深度神经网络的图像分类容易受到对抗扰动的影响。通过向输入图像中添加人为制造的、微小且不可察觉的扰动，图像分类结果很容易被欺骗。作为最有效的防御策略之一，对抗训练被提出以解决分类模型的这一脆弱性；在训练过程中，会生成对抗样本并将其注入训练数据。过去几年中，分类模型的攻击与防御得到了深入研究。语义分割作为分类的扩展，近年来也受到广泛关注。近期研究表明，要生成有效的对抗样本来欺骗分割模型，需要大量攻击迭代。这一观察结果使得分割模型的鲁棒性评估和对抗训练都具有挑战性。在本工作中，我们提出了一种有效且高效的分割攻击方法，称为 SegPGD。此外，我们提供了收敛性分析，以表明在相同攻击迭代次数下，所提出的 SegPGD 能够比 PGD 生成更有效的对抗样本。进一步地，我们提出将 SegPGD 用作分割对抗训练的底层攻击方法。由于 SegPGD 能够生成更有效的对抗样本，使用我们的 SegPGD 进行对抗训练可以提升分割模型的鲁棒性。我们的方案还通过在流行的分割模型架构和标准分割数据集上的实验得到了验证。
英文摘要：
Deep neural network-based image classifications are vulnerable to adversarial perturbations. The image classifications can be easily fooled by adding artificial small and imperceptible perturbations to input images. As one of the most effective defense strategies, adversarial training was proposed to address the vulnerability of classification models, where the adversarial examples are created and injected into training data during training. The attack and defense of classification models have been intensively studied in past years. Semantic segmentation, as an extension of classifications, has also received great attention recently. Recent work shows a large number of attack iterations are required to create effective adversarial examples to fool segmentation models. The observation makes both robustness evaluation and adversarial training on segmentation models challenging. In this work, we propose an effective and efficient segmentation attack method, dubbed SegPGD. Besides, we provide a convergence analysis to show the proposed SegPGD can create more effective adversarial examples than PGD under the same number of attack iterations. Furthermore, we propose to apply our SegPGD as the underlying attack method for segmentation adversarial training. Since SegPGD can create more effective adversarial examples, the adversarial training with our SegPGD can boost the robustness of segmentation models. Our proposals are also verified with experiments on popular Segmentation model architectures and standard segmentation datasets.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
