通过动态估计决策边界曲率，提升黑盒对抗攻击效率。
Curvature Dynamic Black-box Attack: revisiting adversarial robustness via dynamic curvature estimation
- 基于CGBA攻击方法，提出动态曲率估计（DCE）新机制。
- 实证发现决策边界曲率与模型鲁棒性存在统计关联。
- 提出新型攻击方法CDBA，性能优于现有方法。
对抗攻击揭示了深度学习模型的脆弱性。通常认为高曲率会导致粗糙的决策边界，从而降低模型鲁棒性。然而，当前广泛使用的曲率指标是损失函数、输出分数或其他内部参数的曲率，而非决策边界曲率，因为前者可通过二阶导数较容易计算。本文提出一种新的、查询高效的黑盒方法——动态曲率估计（DCE），用于在黑盒设置下估计决策边界曲率。该方法基于已有黑盒攻击方法CGBA，通过对多种分类器进行实验，统计上发现了决策边界曲率与对抗鲁棒性之间的关联。在此基础上，我们进一步提出了曲率动态黑盒攻击（CDBA），利用估计的曲率信息提升了攻击性能。
原文摘要 · Abstract (English)
Adversarial attack reveals the vulnerability of deep learning models. It is assumed that high curvature may give rise to rough decision boundary and thus result in less robust models. However, the most commonly used \textit{curvature} is the curvature of loss function, scores or other parameters from within the model as opposed to decision boundary curvature, since the former can be relatively easily formed using second order derivative. In this paper, we propose a new query-efficient method, dynamic curvature estimation (DCE), to estimate the decision boundary curvature in a black-box setting. Our approach is based on CGBA, a black-box adversarial attack. By performing DCE on a wide range of classifiers, we discovered, statistically, a connection between decision boundary curvature and adversarial robustness. We also propose a new attack method, curvature dynamic black-box attack (CDBA) with improved performance using the estimated curvature.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。