基于GPU的缩放多面体神经网络验证
Scaling Polyhedral Neural Network Verification on GPUs
摘要：
验证神经网络对对抗攻击的鲁棒性对于它们在自动驾驶和医疗诊断等安全关键系统中的可靠采用至关重要。不幸的是，最先进的验证器要么无法扩展到更大的网络，要么太不精确而无法证明其鲁棒性，从而限制了它们的实际采用。在这项工作中，我们引入了GPUPoly，这是一个可扩展的验证器，可以证明比以前更大的深度神经网络的鲁棒性。GPUPoly背后的关键技术见解是设计用于GPU上神经网络验证的自定义、合理的多面体算法。我们的算法利用了GPU的并行性和底层验证任务的固有稀疏性。GPUPoly可扩展到大型网络：例如，它可以在大约34.5 ms内证明1M神经元，34层深度残差网络的鲁棒性。我们相信GPUPoly是朝着现实世界神经网络的实际验证迈出的有希望的一步。
英文摘要：
Certifying the robustness of neural networks against adversarial attacks is essential to their reliable adoption in safety-critical systems such as autonomous driving and medical diagnosis. Unfortunately, state-of-the-art verifiers either do not scale to bigger networks or are too imprecise to prove robustness, limiting their practical adoption. In this work, we introduce GPUPoly, a scalable verifier that can prove the robustness of significantly larger deep neural networks than previously possible. The key technical insight behind GPUPoly is the design of custom, sound polyhedra algorithms for neural network verification on a GPU. Our algorithms leverage the available GPU parallelism and inherent sparsity of the underlying verification task. GPUPoly scales to large networks: for example, it can prove the robustness of a 1M neuron, 34-layer deep residual network in approximately 34.5 ms. We believe GPUPoly is a promising step towards practical verification of real-world neural networks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
