Training data is crucial in ensuring robust neural inference, and deep neural networks (DNNs) are heavily dependent on this assumption. However, DNNs can be exploited by adversaries that facilitate various attacks. Adversarial defenses include several techniques, some of which happen during the preprocessing stages (i.e., noise filtering, etc.). This article analyzes the impact of some preprocessing filters, and proposes a selective preprocessing method which increases robustness and reduces the computational complexity.—Theocharis Theocharides, University of Cyprus

中文翻译：

---

SSCNets：使用安全选择性卷积滤波器增强DNN的可靠性

训练数据对于确保可靠的神经推理至关重要，而深度神经网络（DNN）严重依赖此假设。但是，攻击者可以利用DNN进行各种攻击。对抗防御包括多种技术，其中一些技术发生在预处理阶段（即，噪声过滤等）。本文分析了一些预处理过滤器的影响，并提出了一种选择性的预处理方法，该方法可以提高鲁棒性并降低计算复杂性。-Theocharis Theocharides，塞浦路斯大学