【24h】

Vector Based Genetic Algorithm to optimize predictive analysis in network security

机译:基于向量的遗传算法,以优化网络安全预测分析

获取原文
获取原文并翻译 | 示例
           

摘要

A new Intrusion Detection System (IDS) for network security is proposed making use of a Vector-Based Genetic Algorithm (VBGA) inspired by evolutionary approaches. The novelty in the algorithm is to represent chromosomes as vectors and training data as matrices. This approach allows multiple pathways to calculate fitness function out of which one particular methodology is used and tested. The proposed method uses the overlap of the matrices with vector chromosomes for model building. The fitness of the chromosomes is calculated from the comparison of true and false positives in test data. The algorithm is flexible to train the chromosomes for one particular attack type or to detect the maximum number of attacks. The VBGA has been tested on two datasets (KDD Cup-99 and CTU-13). The proposed algorithm gives high detection rate and low false positives as compared to traditional Genetic Algorithm. A detailed comparative analysis is given of proposed VBGA with the traditional string-based genetic algorithm on the basis of accuracy and false positive rates. The results show that vector based genetic algorithm provides a significant improvement in detection rates keeping false positives at minimum.
机译:建议使用用于网络安全的新的入侵检测系统(IDS),利用来自进化方法的载体的遗传算法(VBGA)。算法中的新颖性是将染色体表示为乘法和训练数据作为矩阵。该方法允许多种途径计算使用和测试一种特定方法的健身功能。所提出的方法使用矩阵的重叠与矢量染色体进行模型建筑。染色体的适应性根据测试数据中的真实和误报的比较计算。该算法是灵活的,用于训练一种特定攻击类型或检测最大攻击次数。 VBGA已在两个数据集(KDD CUP-99和CTU-13)上进行测试。与传统遗传算法相比,所提出的算法具有高检测率和低误报。详细的比较分析是基于准确度和假阳性率的传统串遗传算法的提出的VBGA。结果表明,基于载体的遗传算法在最小的检测速率下提供了显着的改善。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号