Semantic Identification of IoT Devices from Behavioral Primitives
For network security management, this work addresses the problem of device identification when runtime traffic patterns deviate from canonical profiles, offering a more robust alternative to exact matching.
This paper proposes a method for IoT device identification using semantic representations of behavioral primitives from MUD profiles, achieving robust identification under sparse and partial runtime observations. On real traffic traces with over 800,000 flows, semantic ACE matching provides stronger evidence than exact matching during early observation stages and under sparse overlap.
Accurate identification of IoT devices is important for security management and policy enforcement. Existing approaches typically learn device signatures from packets or flow records. These methods operate on low-level communication observations whose traffic patterns may vary across deployments, software versions, and user interactions. This paper studies device identification using Manufacturer Usage Description (MUD) profiles. MUD profiles describe device behavior using Access Control Entries (ACEs), where each ACE represents a behavioral primitive consisting of protocol, endpoint, direction, and port semantics derived from device communication policy. Our contributions are threefold. First, using 28 publicly available MUD profiles containing 1,023 ACE instances, we construct ACE-level semantic representations from compact behavioral text and analyze their geometric properties. ACE-level representations preserve device-level behavioral distinctions more effectively than whole-profile embeddings and remain effective after whitening calibration. Second, we evaluate semantic ACE matching under controlled runtime variations, including unseen ACEs, drifted hostnames, and partial runtime observation. Exact ACE matching performs well when the overlap with the canonical MUD profile remains high, but degrades sharply when the overlap becomes sparse or disappears. In contrast, semantic ACE matching preserves useful identification evidence across these conditions. Third, we evaluate the same approach on real IoT traffic traces comprising more than 800,000 observed flows. Exact overlap remains the strongest signal when stable overlap exists, while semantic ACE matching provides stronger identification evidence during the early stages of observation, frequently retains the correct device among the highest-ranked candidates, and remains effective under sparse-overlap runtime traffic.