ID 原文 译文
57198 提出了一种可以缓解状态空间爆炸的抽象原则，对模型设计过程中的辅助变量、报文字段、自动状态机数量进行科学约简，在尽量不影响验证结果准确度的前提下，降低了模型的复杂度. An abstract principle is proposed to mitigate the explosion of state space. The proposed scheme scientifically reduces the auxiliary variables，message fields and numbers of automatic state machines in the process of model design，and reduces the complexity and size of the model on the premise of minimi- zing the accuracy of verification results.
57199 在此基础上，提出了一种半自动化建模框架，只需用户提供少量必须的输入，不需要学习语法，就可以自动生成具有统一规范的模型，方便研究人员查阅和使用. A semi-automatic modeling framework is proposed thereafter， which can automatically generate models with uniform specifications with only a small amount of input provided by users and no need to learn grammar，which is convenient for researchers to consult and use.
57200 实验结果表明，采用所提的抽象原则和半自动化建模框架创建的模型，可以验证网络协议的相关属性. Experiments show that the model based on the proposed abstract principle and the semi-automatic model- ing framework can verify the properties of the network protocol.
57201 为了提高拟态防御中表决的准确性，提出了一种基于改进层次分析－模糊综合评价( AHP －FCE) 模型的多指标拟态表决算法. In order to improve the accuracy of mimic voting，a multi-index mimic voting algorithm based on the improved analytic hierarchy process －fuzzy comprehensive evaluation( AHP －FCE) model is pro- posed.
57202 针对传统 AHP－FCE 模型中判断矩阵一致性检验的缺点，对判断矩阵的构造方法进行了改进，构造具有一致性的判断矩阵，无须一致性校验和调整. In view of the shortcomings of the consistency check in the traditional model，the proposed algo- rithm improves the construction method of the judgment matrix. It can construct a judgment matrix that must have consistency with no need for consistency check and adjustment.
57203 基于该改进模型，综合分析了拟态表决中的一致度、历史置信度、异构度指标，将拟态表决转化为模糊评价过程. Based on the improved model， the algorithm comprehensively analyzes the consistency，historical confidence，and heterogeneity in the mimic voting，transforming the mimic voting into a fuzzy evaluation process.
57204 仿真结果表明，与一致表决相比，该算法能有效提高表决的正确率，提升拟态系统的整体安全性能. Simulations show that com- pared with consensus voting，the algorithm can effectively improve the accuracy of voting and the overall safety performance of a mimic system.
57205 基于已知数据的机器学习模型在实际异常流量检测任务中不完全可靠，为此，将不同分布的流量分别作为源域和目标域，建立跨域网络异常流量检测框架，提出了基于联合分布适配的迁移学习方法. In order to solve the problem that the machine learning model based on known data is not com- pletely reliable in actual abnormal traffic detection tasks due to the dynamics of the network environment. The different distributed traffic as the source domain and target domain is used to establish a cross-domain framework for abnormal network traffic detection.
57206 通过寻找最优变换矩阵、适配源域与目标域之间的条件概率和边缘概率，实现源域与目标域间的特征迁移，从而解决由于源域与目标域分布差异大所引起的检测准确率下降等问题. The transfer learning method based on joint distribution adaptation is proposed by finding the optimal transformation matrix，adapting the conditional probability and edge probability between the source domain and the target domain，the feature transfer between the source domain and the target domain is realized thereby for solving the problem of the large difference in the distribution of the source domain and the target domain causes problems such as decreased detection accuracy.
57207 实验结果表明，所提方法可以显著提升跨域流量的检测准确率. Experiments show that the proposed method can significantly improve the detection accuracy of cross-domain traffic.