分析深度ReLU网络对高维输入扰动的鲁棒性，给出可量化下界。
Robustness of Deep ReLU Networks to Misclassification of High-Dimensional Data
- 基于输入维度和网络单元总数，推导局部鲁棒性下界。
- 证明高维输入下网络对随机扰动仍具较强抗错能力。
- 适合关注模型安全性的研究人员参考。
我们对参数化网络在随机输入扰动下的鲁棒性进行了理论研究。具体而言，通过量化小幅度加性随机扰动导致误分类的概率，分析了网络在给定输入处的局部鲁棒性。针对具有线性整流单元（ReLU）的深度网络，我们推导出局部鲁棒性的下界，该下界与输入维度及网络总单元数相关。
原文摘要 · Abstract (English)
We present a theoretical study of the robustness of parameterized networks to random input perturbations. Specifically, we analyze local robustness at a given network input by quantifying the probability that a small additive random perturbation of the input leads to misclassification. For deep networks with rectified linear units, we derive lower bounds on local robustness in terms of the input dimensionality and the total number of network units.
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。