arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2109.07593cs.CRcs.LG
收藏

使用监督机器学习的现代网络安全解决方案

Modern Cybersecurity Solution using Supervised Machine Learning

AGH University of Science and Technology(AGH科技大学)

Mustafa Sakhai, Maciej Wielgosz

摘要:

网络安全至关重要,攻击正在迅速增长,检测起来也越来越具有挑战性。传统的防火墙和入侵检测系统,即使它被广泛使用和推荐,但它无法检测到新的攻击,零日攻击,以及与任何配置规则不匹配的流量模式。因此,机器学习(ML)可以成为网络安全领域一种有效且成本降低的解决方案。我们使用Netflow数据集在应用数据分析后提取特征。然后,一个选择过程已被应用到这些功能相互比较。我们的实验重点是如何有效的机器学习算法可以检测机器人流量,恶意软件流量和背景流量。我们设法从一个数据集中获得了0.903的精度值,该数据集包含6.5%的Bot流,1.57%的正常流,0.18%的命令和控制(C&C)流,以及91.7%的背景流,总流量为2,753,884。结果表明,低假阴性与几个假阳性检测。

英文摘要:

Cybersecurity is essential, and attacks are rapidly growing and getting more challenging to detect. The traditional Firewall and Intrusion Detection system, even though it is widely used and recommended but it fails to detect new attacks, zero-day attacks, and traffic patterns that do not match with any configured rules. Therefore, Machine Learning (ML) can be an efficient and cost-reduced solution in cybersecurity. We used Netflow datasets to extract features after applying data analysis. Then, a selection process has been applied to compare these features with one another. Our experiments focus on how efficient machine learning algorithms can detect Bot traffic, Malware traffic, and background traffic. We managed to get 0.903 precision value from a dataset that has 6.5% Bot flows, 1.57% Normal flows, 0.18% Command&Control (C&C) flows, and 91.7% background flows, from 2,753,884 total flows. The results show low false-negative with few false-positive detections.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑