信息安全研究2025，Vol.11Issue(4)：351-357,7.DOI:10.12379/j.issn.2096-1057.2025.04.08
结合序列关联图与GAN的高可用时序数据生成方法
High-utility Time Series Data Generation Method Combining Sequence Correlation Graph and GAN
摘要
Abstract
Long-term time series data is difficult to obtain in reality,which seriously restricts the development of applications such as situational awareness and threat analysis in cyberspace security.Deep learning-driven data generation methods can effectively protect the privacy of original data,where ensuring the high utility and diversity of generated data is crucial.However,existing methods used random splicing of short-term data to construct training data,which cannot ensure that the distribution of generated data meets expectations,affecting the availability of generated data.To address the above problems,this paper proposes a high-utility time series generation method combining sequence correlation graph and generative adversarial network.By constructing sequence correlation graph and probability weighted generative adversarial network,the original data distribution is accurately fitted.Experimental results on multiple real data sets show that the method can generate long-term time series data with high utility and diversity based on short-term original data,showing its great potential in practical applications.关键词
数据生成/数据安全/时序数据/短序列/生成对抗网络Key words
data generation/data security/time series data/short sequence/GAN(generative adversarial network)分类
计算机与自动化引用本文复制引用
万韵伟,程瑶,门元昊..结合序列关联图与GAN的高可用时序数据生成方法[J].信息安全研究,2025,11(4):351-357,7.基金项目
国家242信息安全计划项目(2020A065) （2020A065）
