ID	原文	译文
3503	首先，构建了动态概率攻击图模型，设计了概率攻击图更新算法，使之能够随着时空的推移而周期性更新，从而适应弹性、动态性的云计算环境。	Firstly, a dynamic probabilistic attack graph model was constructed,and a probabilistic attack graph updating algorithm was designed to make it update periodically with the passage of timeand space, so as to adapt to the elastic and dynamic cloud computing environment.
3504	其次，设计了攻击意图推断算法和最大概率攻击路径推断算法，解决了误报、漏报导致的攻击场景错误、断裂等不确定性问题，保证了攻击场景的准确性。	Secondly, an attack intention inference algorithm and a maximum probability attack path inference algorithm were designed to solve the uncertain problems such as error and fracture of attack scenarios caused by false positive or false negative, and ensure the accuracy of attack sce-nario.
3505	同时将攻击场景随动态概率攻击图动态演化，保证了攻击场景的完备性和新鲜性。	Meanwhile, the attack scenario was dynamically evolved along with the dynamic probability attack graph to ensurethe completeness and freshness of the attack scenario.
3506	实验结果表明，所提方法能够适应弹性、动态的云计算环境，还原出攻击者完整的攻击渗透过程，重构出高层次的攻击场景，为构建可监管可追责的云环境提供了一定的依据和参考。	Experimental results show that the proposed method can adapt to the elastic and dynamic cloud environment, restore the penetration process of attacker's and reconstruct high-level attackscenario, and so provide certain references for building supervised and accountable cloud environment.
3507	针对车载环境下有限的网络资源和大量用户需求之间的矛盾，提出了智能驱动的车载边缘计算网络架构，以实现网络资源的全面协同和智能管理。	Given the contradiction between limited network resources and massive user demands in Internet of vehicles,an intelligent vehicular edge computing network architecture was proposed to achieve the comprehensive cooperation and intelligent management of network resources.
3508	基于该架构，设计了任务卸载和服务缓存的联合优化机制，对用户任务卸载以及计算和缓存资源的调度进行了建模。	Based on this architecture, a joint optimization scheme of task offloading and service caching was furtherly devised, which formulated an optimization problem about how to offload tasks and al-locate computation and cache resources.
3509	鉴于车载网络的动态、随机和时变的特性，利用异步分布式强化学习算法，给出了最优的卸载决策和资源管理方案。	In view of the dynamics, randomness and time variation of vehicular networks,an asynchronous distributed reinforcement learning algorithm was employed to obtain the optimal task offloading andresource management policy.
3510	实验结果表明，与其他算法相比，所提算法取得了明显的性能提升。	Simulation results demonstrate that the proposed algorithm achieves significant perfor-mance improvement in comparison with the other schemes.
3511	针对众包结果汇聚中最优排序结果选取的时效性问题，提出了 Worker 权重的高效快速汇聚算法。	To solve the problem of quickly obtaining the optimal ranking result in the crowdsourcing result aggregation,an efficient and effective aggregation algorithm of Worker's weight was proposed.
3512	其中Worker 权重的差分进化算法重点考虑众包 Worker 完成排序任务存在的差异性问题，基于目标函数和约束条件中Worker 完成任务的不确定性和差异性影响，建立基于差分进化算法的 Worker 权重优化模型，	The Worker's weight optimization model based on differential evolution algorithm focused on the uncertainties and differences of Workers completingranking tasks, the uncertainties and differences were reflected in the objective function and constraint conditions of the model.