Evaluating Machine Learning-Based IoT Device Identification Models for Security Applications
Eman Maali
Network and Distributed System Security (NDSS) Symposium 2025 · Day 1 · IoT Security
In an increasingly interconnected world, the proliferation of Internet of Things (IoT) devices presents both convenience and significant security challenges. As these devices become ubiquitous in homes, enterprises, and industrial settings, the ability to accurately identify them on a network is paramount for effective security management. This talk, presented by Eman Maali, a collaborative effort between Imperial College London and Georgia Tech, addresses a critical gap in current IoT security practices: the real-world practicality of machine learning (ML)-based device identification models. The core problem highlighted is the scenario where a network operator needs to identify all IoT devices affected by a newly discovered vulnerability to apply security patches efficiently. The accuracy and robustness of the underlying identification solution are thus of utmost importance.
AI review
Competent, methodologically honest evaluation of ML-based IoT device fingerprinting — 140 experiments, dual-lab testbed, reproducibility-aware model selection. The numbers are real and the degradation findings are damning enough to be useful, but this is ultimately a benchmarking paper dressed as a talk: it diagnoses a known problem more rigorously than most, without delivering a solution.