arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.05362cs.CRcs.LG
收藏

RAPID:基于上下文感知深度学习的鲁棒APT检测与调查

RAPID: Robust APT Detection and Investigation Using Context-Aware Deep Learning

Ben-Gurion University of the Negev(内盖夫本-古里安大学)

Yonatan Amaru, Prasanna Wudali, Yuval Elovici, Asaf Shabtai

AI总结:

本文提出RAPID方法,通过上下文感知异常检测、自监督序列学习和溯源追踪,实现鲁棒且高效的APT检测与调查,显著降低误报并提升精确率和召回率。

摘要:

高级持续性威胁(APT)给组织带来重大挑战,导致数据泄露、财务损失和声誉损害。现有的基于溯源(provenance)的APT检测方法往往面临高误报率、缺乏可解释性以及无法适应不断演变的系统行为等问题。我们提出RAPID,一种基于深度学习的新型方法,用于鲁棒的APT检测与调查,利用上下文感知的异常检测和告警追踪。通过采用自监督序列学习和迭代学习的嵌入表示,我们的方法能够有效适应动态系统行为。溯源追踪的使用既丰富了告警信息,也增强了我们方法的检测能力。我们广泛的评估证明了RAPID在真实场景中的有效性和计算效率。此外,RAPID比最先进的方法实现了更高的精确率和召回率,显著降低了误报。RAPID整合了上下文信息,并促进了从检测到调查的平滑过渡,为安全团队提供详细洞察,以高效应对APT威胁。

英文摘要:

Advanced persistent threats (APTs) pose significant challenges for organizations, leading to data breaches, financial losses, and reputational damage. Existing provenance-based approaches for APT detection often struggle with high false positive rates, a lack of interpretability, and an inability to adapt to evolving system behavior. We introduce RAPID, a novel deep learning-based method for robust APT detection and investigation, leveraging context-aware anomaly detection and alert tracing. By utilizing self-supervised sequence learning and iteratively learned embeddings, our approach effectively adapts to dynamic system behavior. The use of provenance tracing both enriches the alerts and enhances the detection capabilities of our approach. Our extensive evaluation demonstrates RAPID's effectiveness and computational efficiency in real-world scenarios. In addition, RAPID achieves higher precision and recall than state-of-the-art methods, significantly reducing false positives. RAPID integrates contextual information and facilitates a smooth transition from detection to investigation, providing security teams with detailed insights to efficiently address APT threats.

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。

↑