论文标题
超越$ \ ell_p $度量的鲁棒性评估优化
Optimization for Robustness Evaluation beyond $\ell_p$ Metrics
论文作者
论文摘要
对对抗性攻击的深度学习模型的经验评估需要解决非平凡的约束优化问题。解决这些约束问题的流行算法取决于预计的梯度下降（PGD），并且需要对多个超参数进行仔细调整。此外，由于使用分析投影仪，PGD只能处理$ \ ell_1 $，$ \ ell_2 $，$ \ ell_2 $和$ \ ell_ \ eld_ \ infty $攻击模型。在本文中，我们介绍了一种新颖的算法框架，该框架将通用的约束优化求解器Pygranso与约束折叠（PWCF）融合在一起，以增加可靠性和一般性评估。 PWCF 1）在不需要精致的超参数调整的情况下找到优质解决方案，而2）可以处理一般攻击模型，例如一般$ \ ell_p $（$ p \ geq 0 $）和感知攻击，这些算法无法获得基于PGD的算法。
Empirical evaluation of deep learning models against adversarial attacks entails solving nontrivial constrained optimization problems. Popular algorithms for solving these constrained problems rely on projected gradient descent (PGD) and require careful tuning of multiple hyperparameters. Moreover, PGD can only handle $\ell_1$, $\ell_2$, and $\ell_\infty$ attack models due to the use of analytical projectors. In this paper, we introduce a novel algorithmic framework that blends a general-purpose constrained-optimization solver PyGRANSO, With Constraint-Folding (PWCF), to add reliability and generality to robustness evaluation. PWCF 1) finds good-quality solutions without the need of delicate hyperparameter tuning, and 2) can handle general attack models, e.g., general $\ell_p$ ($p \geq 0$) and perceptual attacks, which are inaccessible to PGD-based algorithms.
