用改进的Frank-Wolfe方法高效生成白盒攻击，提升攻击速度与效果。
Empirical evaluation of the Frank-Wolfe methods for constructing white-box adversarial attacks
- 采用无投影的改进Frank-Wolfe算法构建攻击，避免传统投影计算。
- 在MNIST和CIFAR-10上实现更快收敛，攻击成功率更高。
- 适合研究模型鲁棒性或优化攻击效率的工程师与学者。
神经网络的对抗攻击构造是其在各类服务中部署的关键挑战。为评估神经网络的对抗鲁棒性，需要快速高效的攻击构造方法。由于对抗攻击的构建可形式化为特定优化问题，本文从数值优化角度出发，提出使用改进的无投影方法——修正Frank-Wolfe方法，来生成白盒对抗攻击。我们对这些方法进行了理论与数值评估，并与基于投影或几何直觉的标准方法进行比较。实验在MNIST和CIFAR-10数据集上进行，采用多类逻辑回归模型、卷积神经网络（CNN）和视觉变换器（ViT）作为测试模型。
原文摘要 · Abstract (English)
The construction of adversarial attacks for neural networks appears to be a crucial challenge for their deployment in various services. To estimate the adversarial robustness of a neural network, a fast and efficient approach is needed to construct adversarial attacks. Since the formalization of adversarial attack construction involves solving a specific optimization problem, we consider the problem of constructing an efficient and effective adversarial attack from a numerical optimization perspective. Specifically, we suggest utilizing advanced projection-free methods, known as modified Frank-Wolfe methods, to construct white-box adversarial attacks on the given input data. We perform a theoretical and numerical evaluation of these methods and compare them with standard approaches based on projection operations or geometrical intuition. Numerical experiments are performed on the MNIST and CIFAR-10 datasets, utilizing a multiclass logistic regression model, the convolutional neural networks (CNNs), and the Vision Transformer (ViT).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。