ID 原文 译文
40846 针对硬件木马的检测，本文提出一种基于电路结构分析的集成模型。 For the detection of hardware Trojans, an integrated model based on circuit structure analysis is proposed in this paper.
40847 该方法利用遍历的方法提取硬件木马三组门级特征，采用NLP思想与方法和RobustScaler标准化的预处理，将复杂繁琐的电路图转化为向量数据格式， In this method, three groups of gate level features of hardware Trojan were extracted by topological retrieval, and the complex circuit diagram was transformed into vector data format by NLP idea and method and Robust scaler standardized pretreatment.
40848 通过极限梯度提升树和长短期记忆神经网络的集成模型来检测硬件木马。 The hardware Trojan was detected by the integrated model of limit gradient lifting tree and long short memory neural network.
40849 86.5%TPR和97.9%TNR的实验结果，有效说明本方法的高效性和准确性。 The experimental results of 86.5% TPR and 97.9% TNR effectively illustrate the efficiency and accuracy of this method.
40850 针对当前基于卷积神经网络的双目立体匹配算法需要较高的特征提取能力且网络的参数量过多的问题，提出一种基于注意力机制的立体匹配网络， To improve the feature extraction capability of current stereo matching network and reduce the parameter, the multi-scale context attention network for stereo matching network is proposed.
40851 在特征提取阶段采用改进后的通道注意力机制根据通道内所含的信息进行特征加权，同时采用改进的空间金字塔结构实现多尺度特征提取，以提高网络的特征提取能力; In the feature extraction stage, the improvedchannel-wise attention mechanism is used to weight the features based on the information contained in the channel, and the improved spatial pyramid structure is used to achieve multi-scale feature extraction to improve the network's feature extraction ability.
40852 设计3D注意力模块和3D可分离卷积进行视差计算， A three-dimensional attention module and a three-dimensional separable convolution for disparity calculation.
40853 相比于标准卷积不仅可以降低网络的计算参数同时增加了通道维数可以保证匹配精度。 Compared with the standard convolution, the computational parameters of the network can be reduced and the channel dimension can be increased to ensure the matching accuracy.
40854 最后，在Scene Flow数据集、KITTI 2012数据集和KITTI 2015数据集上进行评估，实验表明，本文的网络模型在保证匹配精度的同时有效减少网络的计算参数。 Experiments on Scene Flow datasets, KITTI 2012 datasets and KITTI 2015 datasets show that the network model in this paper can effectively reduce the calculation parameters of the network while ensuring matching accuracy.
40855 目前flash扰动失效测试算法无法检测SONOS型flash存储器的全部扰动失效，特别是对读扰动失效检测的失效覆盖率低，且测试效率不高。 The current Flash disturbance failure test algorithm cannot detect all the disturbance failures of SONOS-type Flash memory, especially the failure coverage of read disturbance failure test is low, and the test efficiency is poor.