论文标题
全球鲁棒性验证网络
Global Robustness Verification Networks
论文作者
论文摘要
深度神经网络的广泛部署虽然在许多领域取得了巨大成功，但却存在严重的安全性和可靠性问题。现有的对抗性攻击生成和自动验证技术无法正式验证网络在全球范围内是否稳健，即输入空间中缺乏对抗性示例。为了解决这个问题，我们使用三个组成部分开发了一个全球鲁棒性验证框架：1）基于新规则的````背部'''发现哪个输入区域通过逻辑推理负责班级分配； 2）一个新的网络体系结构滑动门网络（SDN），启用可行规则的````backpropagation'''; 3）基于区域的全球鲁棒性验证（RGRV）方法。此外，我们证明了方法对合成数据集和真实数据集的有效性。
The wide deployment of deep neural networks, though achieving great success in many domains, has severe safety and reliability concerns. Existing adversarial attack generation and automatic verification techniques cannot formally verify whether a network is globally robust, i.e., the absence or not of adversarial examples in the input space. To address this problem, we develop a global robustness verification framework with three components: 1) a novel rule-based ``back-propagation'' finding which input region is responsible for the class assignment by logic reasoning; 2) a new network architecture Sliding Door Network (SDN) enabling feasible rule-based ``back-propagation''; 3) a region-based global robustness verification (RGRV) approach. Moreover, we demonstrate the effectiveness of our approach on both synthetic and real datasets.
