感知对齐的梯度是否意味着对抗鲁棒性？
Do Perceptually Aligned Gradients Imply Adversarial Robustness?
AI总结：
本文研究感知对齐梯度（PAG）与对抗鲁棒性的关系，提出直接促进PAG的新目标函数，并通过多数据集实验证明PAG与鲁棒性存在双向联系，进而利用梯度对齐提升现有对抗训练方法的鲁棒性。
摘要：
对抗鲁棒分类器具有非鲁棒模型所不具备的特性——感知对齐梯度（Perceptually Aligned Gradients, PAG）。它们相对于输入的梯度与人类感知高度一致。多项工作已将PAG视为鲁棒训练的副产品，但没有人将其作为独立现象加以考虑，也没有研究其自身的影响。在本文中，我们聚焦于这一特性，并检验“感知对齐梯度是否意味着鲁棒性”。为此，我们开发了一个新的目标函数，在训练分类器时直接促进PAG，并检验具有此类梯度的模型是否对对抗攻击更加鲁棒。在多个数据集和架构上的大量实验验证了具有对齐梯度的模型表现出显著的鲁棒性，揭示了PAG与鲁棒性之间令人惊讶的双向联系。最后，我们表明更好的梯度对齐会带来更高的鲁棒性，并利用这一观察结果来提升现有对抗训练技术的鲁棒性。
英文摘要：
Adversarially robust classifiers possess a trait that non-robust models do not -- Perceptually Aligned Gradients (PAG). Their gradients with respect to the input align well with human perception. Several works have identified PAG as a byproduct of robust training, but none have considered it as a standalone phenomenon nor studied its own implications. In this work, we focus on this trait and test whether \emph{Perceptually Aligned Gradients imply Robustness}. To this end, we develop a novel objective to directly promote PAG in training classifiers and examine whether models with such gradients are more robust to adversarial attacks. Extensive experiments on multiple datasets and architectures validate that models with aligned gradients exhibit significant robustness, exposing the surprising bidirectional connection between PAG and robustness. Lastly, we show that better gradient alignment leads to increased robustness and harness this observation to boost the robustness of existing adversarial training techniques.
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。
