Recent focus on robustness to adversarial attacks for deep neural networks produced a large variety of algorithms for training robust models. Most of the effective algorithms involve solving the min-max optimization problem for training robust models (min step) under worst-case attacks (max step). However, they often suffer from high computational cost from running several inner maximization iterations (to find an optimal attack) inside every outer minimization iteration. Therefore, it becomes difficult to readily apply such algorithms for moderate to large size real world data sets. To alleviate this, we explore the effectiveness of iterative descent-ascent algorithms where the maximization and minimization steps are executed in an alternate fashion to simultaneously obtain the worst-case attack and the corresponding robust model. Specifically, we propose a novel discrete-time dynamical system-based algorithm that aims to find the saddle point of a min-max optimization problem in the presence of uncertainties. Under the assumptions that the cost function is convex and uncertainties enter concavely in the robust learning problem, we analytically show that our algorithm converges asymptotically to the robust optimal solution under a general adversarial budget constraints as induced by $\ell_p$ norm, for $1\leq p\leq \infty$. Based on our proposed analysis, we devise a fast robust training algorithm for deep neural networks. Although such training involves highly non-convex robust optimization problems, empirical results show that the algorithm can achieve significant robustness compared to other state-of-the-art robust models on benchmark data sets.
翻译:最近,人们关注强力和对敌攻击对深神经网络的影响,为培养稳健模型提出了各种各样的算法。大多数有效的算法都涉及解决在最坏情况下培训强健模型的最小最大优化问题(最小步),但在最坏情况下(最大步),培训强健模型(最小步)的最小最大优化问题。然而,在每一个外部最小化的迭代中,它们往往会遇到高计算成本问题。因此,很难为中到大规模的实际世界数据集迅速应用这种算法。为了缓解这一点,我们探索了迭代性下层增益算法的有效性,在那里,以替代方式执行最大化和最小化步骤,同时获得最坏攻击和相应的强健健型模型。具体地说,我们提出了一个新的离散时间动态系统基算法,目的是在存在不确定性的情况下找到微负负最大优化问题(找到最佳攻击 最佳攻击 ) 。根据这种假设,成本函数是螺旋和不确定性的,在稳健健的世界数据集中,我们的分析显示我们的算法与最稳健的内压最佳解决方案相趋直地结合,在一般的平压预算分析中,通过高压预算规范显示我们高正对冲预算限制。