arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.06452cs.CRcs.LG
收藏

在Linux内核中使用机器学习进行勒索软件检测

Ransomware Detection Using Machine Learning in the Linux Kernel

Orange Polska(波兰Orange公司);Orange(Orange公司)

Adrian Brodzik, Tomasz Malec-Kruszyński, Wojciech Niewolski, Mikołaj Tkaczyk, Krzysztof Bocianiak, Sok-Yen Loui

AI总结:

针对Linux云环境面临的高速勒索软件攻击威胁,提出基于eBPF在内核层收集系统调用信息并部署决策树、多层感知器两种ML模型的检测方案,基准测试表明该方法在延迟和准确率上优于用户空间模型。

摘要:

基于Linux的云环境已成为勒索软件攻击的高价值目标,这类攻击正以前所未有的速度采用各类加密方案。为满足实时勒索软件防护的迫切需求,我们提出利用扩展伯克利包过滤器(extended Berkeley Packet Filter,eBPF)收集活跃进程的系统调用信息,并直接在内核层面对数据进行推断。本研究在eBPF中实现了两种机器学习(Machine Learning,ML)模型:决策树与多层感知器。通过将延迟和准确率与用户空间的对应模型进行基准测试,我们的结果凸显了该方法的有效性。

英文摘要:

Linux-based cloud environments have become lucrative targets for ransomware attacks, employing various encryption schemes at unprecedented speeds. Addressing the urgency for real-time ransomware protection, we propose leveraging the extended Berkeley Packet Filter (eBPF) to collect system call information regarding active processes and infer about the data directly at the kernel level. In this study, we implement two Machine Learning (ML) models in eBPF - a decision tree and a multilayer perceptron. Benchmarking latency and accuracy against their user space counterparts, our findings underscore the efficacy of this approach.

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。

↑