ID	原文	译文
4493	结果表明，所提方法大大降低了访问控制策略的长度、数量和复杂度，提高了访问控制策略冗余与冲突检测的效率以及访问控制策略评估的效率。	It showes that the reconstruction method for accesscontrol policy greatly reduces the number, size and complexity of access control policy, improves the efficiency of accesscontrol policy redundancy and collision detection, and the efficiency of access control evaluation.
4494	针对现有无人机（UAV）空地信道几何统计模型（GBSM）对信号到达角和出射角分布的假设过于理想，无法准确描述 UAV 空地传播环境的空间统计特性，影响建模准确性的问题，面向基于圆柱散射体的 UAV 三维空地信道模型，从俯仰面和水平面详细分析了到达角和出射角对应散射区域的空间几何特征，进而推导得到角度分布的概率密度函数。	To cope with the problem that the distribution assumptions of arrival angle and departure angle in existinggeometry-based stochastic modeling (GBSM) for the unmanned aerial vehicle (UAV) air-to-ground (A2G) channel aretoo ideal to describe the spatial statistical property of the UAV A2G propagation environment precisely, considering the three-dimensional (3D) cylindrical A2G channel model, the spatial geometric characteristics of scattering regions were investigated analytically as corresponding to the angles of arrival and departure in both elevation and azimuth planes,which derived the probability density function (PDF) for the distribution of each angle.
4495	通过仿真研究了信道模型的多种参数对概率密度函数的影响，证明了所提成果能够准确地刻画 UAV 空地信道到达角和出射角的分布，可为空地通信信道的准确建模提供支撑。	The effects of various parametersof channel model on the PDF were studied and simulation results prove that the derived PDF can describe the spatial sta-tistical properties of UAV A2G channels more accurately, and can support the modeling of A2G communication channelswell.
4496	针对如何保护控制器，尤其是骨干控制器免受安全威胁与攻击，提高 SDN 控制平面的安全性，提出一种基于最小代价路径的交换机迁移算法。	In order to protect the controller, especially the controller in backbone network, from security threats and at-tacks, improve the security of the software-defined network (SDN) control plane, a switch migration algorithm based onminimum cost path was proposed.
4497	在迁移模型中加入负载预测模块，预测模块执行控制器负载预测算法，得到负载预测矩阵，然后根据负载预测矩阵确定迁出、目标控制器集合。	A load prediction module was added to the migration model, which executed a con-troller load prediction algorithm to obtain a load prediction matrix, and then a migration-target controller set was deter-mined according to the load prediction matrix.
4498	利用改进的迪杰斯特拉算法确定最小代价路径，根据控制器的负载状态和待迁移交换机的流量优先级，在最小代价路径中确定最优迁移交换机集合，同时针对迁移过程中可能产生的孤立节点问题给出了解决方案。	The improved Dijkstra algorithm was used to determine the minimum costpath. According to the load state of the controller and the traffic priority of the switch to be migrated, the optimal migra-tion switch set was determined. The problem of isolated nodes was solved that may occur during the migration process.
4499	实验结果表明，所提算法确定的迁移触发时机、迁出控制器和目标控制器更加合理，减少了迁移次数和代价，增强了控制器的安全性，提高了控制器性能。	The experimental results show that the migration timing of the algorithm is more reasonable, the selection of the migra-tion controller and the target controller is more reasonable, the load balancing of the control plane is realized, the number of migrations and cost are reduced, and the performance of the controller is improved.
4500	针对监督式神经网络测试网络威胁时需根据数据类别标记进行建模的局限性，提出了一种基于无监督多源数据特征解析的网络威胁态势评估方法。	Aiming at the limitations of supervised neural network in the network threat testing task relying on data cate-gory tagging, a network threat situation evaluation method based on unsupervised multi-source data feature analysis wasproposed.
4501	首先，设计了一个面向安全威胁评估的变分自动编码器−生成式对抗网络（V-G），将只包含正常网络流量的训练数据集输入 V-G 的网络集合层进行模型训练，并计算各层网络输出的重构误差。	Firstly, a variant auto encoder-generative adversarial network (V-G) for security threat assessment was de-signed. The training data set containing only normal network traffic was input to the network collection layer of V-G toperform the model training, and the reconstruction error of the network output of each layer was calculated.
4502	然后，通过输出层的三层变分自动编码器重构误差学习并获取训练异常阈值，使用包含异常网络流量的测试数据集测试分组威胁并统计每组测试的威胁发生概率。	Then, the re-construction error learning was performed by the three-layer variation automatic encoder of the output layer, and thetraining abnormal threshold was obtained. The packet threat was tested by using the test data set containing the abnormalnetwork traffic, and the probability of occurrence of the threat of each group of tests was counted.