ID 原文 译文
16685 可以抵抗相关密钥攻击； And it can resist the related-key attack.
16686 更进一步地构造出了5轮不可能差分特征链，并利用其进行区分攻击； Furthermore, 5 rounds of impossible differential characteristic areconstructed and used to distinguish attacks.
16687 求得算法的活性S盒下界为6，概率约为2–21； The lower bound of the active S-box is 6, and the probability isabout 2–21.
16688 算法存在5轮零相关线性特征。 There are 5 rounds of linear characteristic with zero-correlation.
16689 针对传统级联失效模型中冗余参数固定不变的问题，该文综合考虑节点受攻击程度不同和失效过程中网络拓扑的动态变化，建立了基于节点冗余容量动态控制(DRC)的级联失效模型。 In View of the problem of fixed redundancy parameters in the traditional cascade failure model, this paper comprehensively considers the different attack levels of nodes and the dynamic changes of the network topology during the failure process, and establishes a cascading failure model based on Dynamic control of nodeRedundancy Capacity (DRC).
16690 通过定义网络相变临界因子 衡量节点失效引发级联失效的概率，分析了网络鲁棒性与 之间的相关性，并结合度分布函数详细推导了 的解析表达式，基于解析表达式提出了两种网络鲁棒性提升策略。 By defining the critical factor  of the phase transition of the network to measure the probability of node failure leading to cascading failure, the correlation between network robustness and  is analyzed, and the analytic expression of  is derived in detail by combining degree distribution function. Based on analytic expressions, two network robustness enhancement strategies are proposed.
16691 仿真结果表明，在模型网络和真实网络中，根据被攻击节点度的不同，通过调整节点初始负载参数 可以有效提高目标网络的鲁棒性； The simulation results show that in model network and real network, the robustness of target network can beeffectively improved by adjusting the initial load parameter  of nodes according to the difference of degree ofnodes under attack.
16692 DRC模型下级联失效传播范围较Motter-Lai(ML)模型显著减小。 The failure propagation range of DRC model is significantly reduced compared withMotter-Lai (ML) model.
16693 针对车辆轨迹预测中节点序列的时序特性和实际路网中的空间关联性，该文提出一种基于深度置信网络和SoftMax (DBN-SoftMax)轨迹预测方法。 For the temporal features of trajectory intersection sequence and spatial correlation of the actual roadnetwork, a trajectory prediction method based on the Deep Belief Networks and SoftMax (DBN-SoftMax) isproposed.
16694 首先，考虑到轨迹在节点集合中的强稀疏性和一般特征学习方法对新特征的泛化能力不足，该文利用深度置信网络(DBN)较强的无监督特征学习能力，达到提取轨迹局部空间特性的目的； At first, considering the sparsity of trajectory in an intersection set and the insufficiency ofgeneralization ability in general feature learning methods for new features, the strong unsupervised featurelearning ability of Deep Belief Network (DBN) is used to extract the local spatial features of trajectory.