基于大数据的Web入侵风险预测

发布时间：2018-09-04 09:58

【摘要】：为了提高网络大数据的安全性能,进行Web入侵风险预测,提出基于非平稳性盲源分离的大数据的Web入侵检测模型进行风险预测估计。构建大数据的Web入侵信息测量模型,对Web大数据信息流进行二维信号拟合,采用非平稳性高斯独立平均统计量进行入侵信息判别,实现Web入侵风险预测模型改进设计。仿真结果表明,采用该方法进行大数据的Web入侵检测的准确检测概率较高,风险预测的精度高于传统模型。
[Abstract]:In order to improve the security performance of big data network and predict the Web intrusion risk, a Web intrusion detection model based on non-stationary blind source separation was proposed to estimate the risk. This paper constructs big data's Web intrusion information measurement model, carries on the two-dimensional signal fitting to the Web big data information flow, discriminates the intrusion information by using the non-stationary Gao Si independent average statistic, realizes the improved design of the Web intrusion risk prediction model. The simulation results show that the accurate detection probability of big data's Web intrusion detection is higher and the precision of risk prediction is higher than that of traditional model.
【作者单位】：广州科技贸易职业学院;西南民族大学计算机科学与技术学院;
【基金】：国家自然科学基金(60702075) 广东省高职高专云计算与大数据专业委员会教育科研课题(GDYJSKT14-04)
【分类号】：TP311.13;TP393.08

【相似文献】