论文标题
Debona：分离边界网络分析，以实现更紧密的界限和更快的对抗性鲁棒性证明
Debona: Decoupled Boundary Network Analysis for Tighter Bounds and Faster Adversarial Robustness Proofs
论文作者
论文摘要
神经网络通常用于安全至关重要的现实世界应用中。不幸的是，预测的输出通常对小型敏感，并且可能无法察觉到输入数据。因此，证明不存在这种对抗性例子，或者提供具体的实例，对于确保安全应用程序至关重要。由于列举和测试所有潜在的对抗示例在计算上是不可行的，因此已经开发了验证技术，以使用网络激活的高估来提供数学上有声明的证据证明其缺失。我们提出了一种改进的技术，用于计算这些节点值的紧密上限和下限，基于通过彼此独立地计算两个界限获得的灵活性的提高。此外，我们通过重新实现原始最新软件“神经化”的一部分来获得额外的改进，从而更快地进行了分析。这些改编将必要的运行时降低了94％，并允许对以前太复杂的网络和输入进行成功的搜索。我们提供了卷积网络中最大通量层上紧密和下限的证明。为了确保广泛的可用性，我们开放了实施“ debona”，既具有特定实现的增强功能，又具有精制的边界计算，以更快，更精确的结果。
Neural networks are commonly used in safety-critical real-world applications. Unfortunately, the predicted output is often highly sensitive to small, and possibly imperceptible, changes to the input data. Proving that either no such adversarial examples exist, or providing a concrete instance, is therefore crucial to ensure safe applications. As enumerating and testing all potential adversarial examples is computationally infeasible, verification techniques have been developed to provide mathematically sound proofs of their absence using overestimations of the network activations. We propose an improved technique for computing tight upper and lower bounds of these node values, based on increased flexibility gained by computing both bounds independently of each other. Furthermore, we gain an additional improvement by re-implementing part of the original state-of-the-art software "Neurify", leading to a faster analysis. Combined, these adaptations reduce the necessary runtime by up to 94%, and allow a successful search for networks and inputs that were previously too complex. We provide proofs for tight upper and lower bounds on max-pooling layers in convolutional networks. To ensure widespread usability, we open source our implementation "Debona", featuring both the implementation specific enhancements as well as the refined boundary computation for faster and more exact~results.
