Crafting adversarial examples is crucial for evaluating and enhancing the robustness of Deep Neural Networks (DNNs), presenting a challenge equivalent to maximizing a non-differentiable 0-1 loss function. However, existing single objective methods, namely adversarial attacks focus on a surrogate loss function, do not fully harness the benefits of engaging multiple loss functions, as a result of insufficient understanding of their synergistic and conflicting nature. To overcome these limitations, we propose the Multi-Objective Set-based Attack (MOS Attack), a novel adversarial attack framework leveraging multiple loss functions and automatically uncovering their interrelations. The MOS Attack adopts a set-based multi-objective optimization strategy, enabling the incorporation of numerous loss functions without additional parameters. It also automatically mines synergistic patterns among various losses, facilitating the generation of potent adversarial attacks with fewer objectives. Extensive experiments have shown that our MOS Attack outperforms single-objective attacks. Furthermore, by harnessing the identified synergistic patterns, MOS Attack continues to show superior results with a reduced number of loss functions. Our code is available at https://github.com/pgg3/MOS-Attack.

翻译：构造对抗样本对于评估和增强深度神经网络（DNNs）的鲁棒性至关重要，其挑战等同于最大化一个不可微的0-1损失函数。然而，现有的单目标方法（即对抗攻击）专注于替代损失函数，未能充分利用多个损失函数协同作用的优势，这源于对其协同与冲突关系理解的不足。为克服这些局限，我们提出了基于集合的多目标攻击（MOS Attack），这是一种新颖的对抗攻击框架，它利用多个损失函数并自动揭示其相互关系。MOS Attack采用基于集合的多目标优化策略，能够在无需额外参数的情况下整合大量损失函数。它还能自动挖掘不同损失间的协同模式，从而以更少的目标函数生成强效的对抗攻击。大量实验表明，我们的MOS Attack优于单目标攻击方法。此外，通过利用已识别的协同模式，MOS Attack在减少损失函数数量的情况下仍能保持优越的性能。我们的代码发布于 https://github.com/pgg3/MOS-Attack。