增强输出多样性改进基于共轭梯度的对抗攻击
Enhancing Output Diversity Improves Conjugate Gradient-based Adversarial Attacks
AI总结：
本文提出 ReACG 攻击方法，通过自动调整搜索方向和步长来增大连续搜索点距离，从而增强输出多样性，在 ImageNet 模型上取得优于 ACG 的攻击性能。
摘要：
深度神经网络容易受到对抗样本的影响，在此背景下，生成对抗样本的对抗攻击已被广泛研究。现有研究表明，提高模型输出的多样性有助于改善攻击性能。本研究聚焦于自动共轭梯度（Auto Conjugate Gradient，ACG）攻击，该方法受共轭梯度法启发，具有较高的多样化性能。我们假设增大两个连续搜索点之间的距离会增强输出多样性。为验证该假设，我们提出了 Rescaling-ACG（ReACG），该方法自动修改对两个连续搜索点之间距离有显著影响的两个组成部分，包括搜索方向和步长。ReACG 表现出比 ACG 更高的攻击性能，并且对于具有多个分类类别的 ImageNet 模型尤其有效。实验结果表明，两个连续搜索点之间的距离能够增强输出多样性，并可能有助于开发新的强效攻击方法。代码可在 \url{https://github.com/yamamura-k/ReACG} 获取。
英文摘要：
Deep neural networks are vulnerable to adversarial examples, and adversarial attacks that generate adversarial examples have been studied in this context. Existing studies imply that increasing the diversity of model outputs contributes to improving the attack performance. This study focuses on the Auto Conjugate Gradient (ACG) attack, which is inspired by the conjugate gradient method and has a high diversification performance. We hypothesized that increasing the distance between two consecutive search points would enhance the output diversity. To test our hypothesis, we propose Rescaling-ACG (ReACG), which automatically modifies the two components that significantly affect the distance between two consecutive search points, including the search direction and step size. ReACG showed higher attack performance than that of ACG, and is particularly effective for ImageNet models with several classification classes. Experimental results show that the distance between two consecutive search points enhances the output diversity and may help develop new potent attacks. The code is available at \url{https://github.com/yamamura-k/ReACG}
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。
