ID	原文	译文
4573	分析结果表明，GRANULE 算法存在144 个不同的 7 轮不可能差分区分器；	The analysis results show that there are 144 different 7-round impossi-ble differential distinguishers in the GRANULE, and 52 different 9-round impossible differential distinguishers in theMANTRA.
4574	MANTRA 算法存在 52 个不同的 9 轮不可能差分区分器。与已有结果相比较，新发现的区分器轮数均是目前最高的。	Compared with the existing results, the rounds of the proposed distinguisher is currently the highest.
4575	针对移动恶意软件数量和种类的急剧增加给移动用户的信息安全带来的巨大挑战，提出了一种基于值导数 GRU 的移动恶意软件流量检测方法，旨在解决基于 RNN 的移动恶意软件流量检测方法难以捕获网络异常流量的动态变化和关键信息的问题。	For the dramatic increase in the number and variety of mobile malware had created enormous challenge forinformation security of mobile network users, a value-derivative GRU-based mobile malware traffic detection approachwas proposed in order to solve the problem that it was difficult for a RNN-based mobile malware traffic detection ap-proach to capture the dynamic changes and critical information of abnormal network traffic.
4576	值导数 GRU 算法通过引入“累计状态变化”的概念，可以同时描述移动网络恶意流量的低阶和高阶动态变化信息。	The low-order and high-orderdynamic change information of the malicious network traffic could be described by the value-derivative GRU approach atthe same time by introducing the concept of “accumulated state change”.
4577	此外，通过增设池化层使算法可以捕获移动恶意流量的关键信息。	In addition, a pooling layer could ensure that thealgorithm can capture key information of malicious traffic.
4578	最后，通过仿真实验分析累计状态变化、隐藏层和池化层对于值导数 GRU 算法性能的影响。	Finally, simulation were performed to verify the effect of accu-mulated state changes, hidden layers, and pooling layers on the performance of the value-derivative GRU algorithm.
4579	实验表明，基于值导数 GRU的移动恶意软件流量检测方法拥有较高的检测准确率。	Exper-iments show that the mobile malware traffic detection approach based on value-derivative GRU has high detection accuracy.
4580	针对车到万物（V2X）场景下复杂的网络状态与海量的计算数据为车载网络带来的时延能耗增加和服务质量下降的严峻问题，构建了移动边缘计算（MEC）和软件定义网络（SDN）相结合的车载网络框架。	To address the serious problem of delay and energy consumption increase and service quality degradationcaused by complex network status and huge amounts of computing data in the scenario of vehicle-to-everything (V2X), avehicular network architecture combining mobile edge computing (MEC) and software defined network (SDN) was con-structed.
4581	MEC 将云服务下沉至无线网络边缘从而弥补了远程云计算所带来时延抖动，SDN 控制器可从全局角度感知网络信息，灵活地调度资源，控制卸载流量。	MEC sinks cloud serviced to the edge of the wireless network to compensate for the delay fluctuation caused byremote cloud computing. The SDN controller could sense network information from a global perspective, flexibly sched-ule resources, and control offload traffic.
4582	为了进一步降低系统开销，提出一种联合任务卸载与资源分配机制，对基于 MEC的 V2X 卸载与资源分配进行建模，给出了最优卸载决策、通信和计算资源分配方案。	To further reduce the system overhead, a joint task offloading and resource al-location scheme was proposed. By modeling the MEC-based V2X offloading and resource allocation, the optimal of-floading decision, communication and computing resource allocation scheme were derived.