SmartX Intelligent Sec: A Security Framework Based on Machine Learning and eBPF/XDP
Talaya Farasat, JongWon Kim, Joachim Posegga

TL;DR
SmartX Intelligent Sec is a novel security framework that combines eBPF/XDP for efficient network traffic handling with BiLSTM deep learning for real-time threat detection, enhancing ICT infrastructure security.
Contribution
It introduces an innovative framework integrating lightweight packet filtering with deep learning-based threat detection for the first time.
Findings
Real-time threat detection with high accuracy
Efficient filtering of malicious traffic
Automated network security operations
Abstract
Information and Communication Technologies (ICT) infrastructures are becoming increasingly complex day by day, facing numerous challenges to support the latest networking paradigms. Security is undeniably a critical component for the effective functioning of these advanced ICT infrastructures. By considering the current network security challenges, we propose SmartX Intelligent Sec, an innovative intelligent security framework. SmartX Intelligent Sec leverages a combination of the lightweight extended Berkeley Packet Filter/eXpress Data Path (eBPF/XDP) for efficient network packet capturing and filtering malicious network traffic, and a Bidirectional Long Short-Term Memory (BiLSTM) classifier for network threat detection. Our real-time prototype demonstrates that SmartX Intelligent Sec offers comprehensive automation features, enabling continuous network packet capturing, effective…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsNetwork Security and Intrusion Detection
