Real-time integrity check for GPU accelerated neural networks

Techniques, among other things, for randomized real-time integrity check of GPU accelerated neural networks are described. A method includes generating an input data stream, wherein the input data stream includes sensor data associated with an autonomous vehicle. The method includes inserting input test data into an input data stream during operation of the autonomous vehicle, wherein the input data stream is input to a neural network accelerated by a graphics processing unit. The output data stream from the neural network is compared to a predetermined output corresponding to the input data stream, and the integrity of the neural network accelerated by the graphics processing unit is verified. 描述了用于GPU加速神经网络的随机化实时完整性检查的技术等。一种方法包括生成输入数据流，其中该输入数据流包括与自主运载工具相关联的传感器数据。该方法包括在自主运载工具的操作期间将输入测试数据插入到输入数据流中，其中该输入数据流被输入到由图形处理单元加速的神经网络。将来自神经网络的输出数据流与同输入数据流相对应的预定输出进行比较，并且验证由图形处理单元加速的神经网络的完整性。