Reproduce “Intelligent ARP Spoofing Detection using Multi-layered Machine Learning (ML) Techniques for IoT Networks” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Anas Ali, Mubashar Husain, Peter Hans
A multi-layered machine learning framework is introduced for real-time ARP spoofing detection within IoT networks. The system achieved over 97% detection accuracy and maintained a false positive rate below 2.3%, demonstrating a balance of computational efficiency and detection robustness.
Key insights
- Distributing detection responsibilities across a hierarchical architecture allows for balancing robust accuracy with the computational constraints inherent to IoT devices.
- Protocol-specific feature engineering, focusing on ARP packet dynamics, provides more targeted and effective indicators of spoofing compared to generic network features.
- The combination of lightweight edge classifiers and powerful central ensemble models significantly refines detection capabilities and reduces false positives.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.