论文标题
MILR：数学诱导的层恢复用于明文空间误差CNNS
MILR: Mathematically Induced Layer Recovery for Plaintext Space Error Correction of CNNs
论文作者
论文摘要
面对自然发生故障以及安全攻击，卷积神经网络（CNN）在任务关键系统中的使用增加了对强大和弹性网络的需求。缺乏鲁棒性和弹性会导致不可靠的推理结果。解决CNN鲁棒性的当前方法需要修改硬件，网络修改或网络重复。本文提出了基于软件的CNN错误检测和误差校正系统，该系统可以从单个和多位误差中对网络进行自我修复。自我修复功能基于层的输入，输出和参数（权重）之间的数学关系，利用这些关系允许在整个层和网络中恢复错误的参数（权重）。 MILR适用于明文空间误差校正（PSEC），鉴于其在CNN中纠正全重重甚至全层错误的能力。
The increased use of Convolutional Neural Networks (CNN) in mission critical systems has increased the need for robust and resilient networks in the face of both naturally occurring faults as well as security attacks. The lack of robustness and resiliency can lead to unreliable inference results. Current methods that address CNN robustness require hardware modification, network modification, or network duplication. This paper proposes MILR a software based CNN error detection and error correction system that enables self-healing of the network from single and multi bit errors. The self-healing capabilities are based on mathematical relationships between the inputs,outputs, and parameters(weights) of a layers, exploiting these relationships allow the recovery of erroneous parameters (weights) throughout a layer and the network. MILR is suitable for plaintext-space error correction (PSEC) given its ability to correct whole-weight and even whole-layer errors in CNNs.
