基于影子价格的快速神经网络验证
Fast Neural Network Verification via Shadow Prices
摘要：
为了在安全关键设置中使用神经网络，提供运行时操作的保证至关重要。最近关于ReLU网络的工作试图验证属于有界框的输入是否会产生一些不期望的输出。输入分裂过程是一种特殊类型的验证机制，它通过递归地将输入集划分为更小的集合来实现。这些方法的效率很大程度上取决于盒子在验证属性之前必须经历的分裂次数。在这项工作中，我们提出了一种新的技术的基础上，充分利用影子价格的问题，产生一个更有效的生成分裂比国家的最先进的信息。机载防撞系统（ACAS）基准验证任务的结果显示，产生的分区，大大减少了计算时间的相当大的减少。这些结果为包括视觉和控制在内的各种机器学习应用程序的改进验证方法打开了大门。
英文摘要：
To use neural networks in safety-critical settings it is paramount to provide assurances on their runtime operation. Recent work on ReLU networks has sought to verify whether inputs belonging to a bounded box can ever yield some undesirable output. Input-splitting procedures, a particular type of verification mechanism, do so by recursively partitioning the input set into smaller sets. The efficiency of these methods is largely determined by the number of splits the box must undergo before the property can be verified. In this work, we propose a new technique based on shadow prices that fully exploits the information of the problem yielding a more efficient generation of splits than the state-of-the-art. Results on the Airborne Collision Avoidance System (ACAS) benchmark verification tasks show a considerable reduction in the partitions generated which substantially reduces computation times. These results open the door to improved verification methods for a wide variety of machine learning applications including vision and control.
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。
