ID	原文	译文
4143	为了解决网络中节点设备异常检测、智能运维、根因分析等问题，针对链路时延、网络吞吐率、设备内存使用率等时序数据，提出了一种基于图的门控卷积编解码异常检测模型。	To solve the problems of anomaly detection, intelligent operation, root cause analysis of node equipment in thenetwork, a graph-based gated convolutional codec anomaly detection model was proposed for time series data such aslink delay, network throughput, and device memory usage.
4144	考虑网络场景的实时性需求以及网络拓扑连接关系对时序数据的影响，基于门控卷积对时序数据并行提取时间维度特征并通过图卷积挖掘空间依赖关系。	Considering the real-time requirements of network scenariosand the impact of network topology connections on time series data, the time dimension features of time series were ex-tracted in parallel based on gated convolution and the spatial dependencies were mined through graph convolution.
4145	基于时空特征提取模块组成的编码器对原始输入时序数据编码后，卷积模块组成的解码器用于重构时序数据。	After the encoder composed of the spatio-temporal feature extraction module encoded the original input time series data, thedecoder composed of the convolution module was used to reconstruct the time series data.
4146	原始数据和重构数据间的残差进一步用于计算异常分数并检测异常。	The residuals between theoriginal data and the reconstructed data were further used to calculate the anomaly score and detect anomalies.
4147	在公开数据和模拟仿真平台上的实验表明，所提模型相对于目前的时间序列异常检测基准模型具有更高的识别准确率。	Experi-ments on public data and simulation platforms show that the proposed model has higher recognition accuracy than thecurrent time series anomaly detection benchmark algorithm.
4148	针对汽车的网络攻击不仅会造成隐私泄露和经济损失，严重情况下还会危及生命安全，甚至上升为国家公共安全问题，因此智能网联车网络安全问题已成为当前研究的热点。	Cyber attacks on vehicles not only cause privacy leaks and economic losses but also endanger human life andeven rise to national public safety issues. Therefore, the research on the cybersecurity of intelligent and connected vehicle(ICV) has become a research hot spot.
4149	首先，对智能网联车中车载网络的结构现状和特点进行了介绍，阐述了车载网络安全面临的设计约束和挑战。	Firstly, the structural status and characteristics of the in-vehicle network (IVN) inICV were introduced, and the challenges and constraints of cybersecurity enhancement design for IVN were also pre-sented.
4150	其次，结合车载网络当前面临的功能安全和信息安全问题，综述了近年来车载网络安全方面国内外最新研究进展。	Secondly, focusing on the current functional safety and cybersecurity issues of IVN, a survey of the current cy-bersecurity enhancement researches for IVN was conducted.
4151	最后，从车载网络结构的特点出发，从标准建设、功能安全和信息安全 3 个方面，围绕智能网联车网络信息安全问题指出了一些重要的研究方向和建议。	Finally, according to the characteristics of the IVN structure,some important research directions and suggestions about cybersecurity problems of ICV were pointed out from the threeaspects of standard construction, functional safety and cybersecurity.
4152	为提高行人交互中轨迹预测速度、精度与模型可解释性，提出了一种基于社会注意力机制的 GAN 模型。	In order to improve the speed, accuracy and model interpretability of trajectory prediction in pedestrian inte-raction, a GAN model based on social attention mechanism was proposed.