Lumos: Identifying and Localizing Diverse Hidden IoT Devices in an Unfamiliar Environment

Hidden IoT devices are increasingly being used to snoop on users in hotel rooms or AirBnBs. We envision empowering users entering such unfamiliar environments to identify and locate (e.g., hidden camera behind plants) diverse hidden devices (e.g., cameras, microphones, speakers) using only their personal handhelds. What makes this challenging is the limited network visibility and physical access that a user has in such unfamiliar environments, coupled with the lack of specialized equipment. This paper presents Lumos, a system that runs on commodity user devices (e.g., phone, laptop) and enables users to identify and locate WiFi-connected hidden IoT devices and visualize their presence using an augmented reality interface. Lumos addresses key challenges in: (1) identifying diverse devices using only coarse-grained wireless layer features, without IP/DNS layer information and without knowledge of the WiFi channel assignments of the hidden devices; and (2) locating the identified IoT devices with respect to the user using only phone sensors and wireless signal strength measurements. We evaluated Lumos across 44 different IoT devices spanning various types, models, and brands across six different environments. Our results show that Lumos can identify hidden devices with 95% accuracy and locate them with a median error of 1.5m within 30 minutes in a two-bedroom, 1000 sq. ft. apartment. Compatible with Approach Personal Handhelds Limited Network Access Diverse Devices Localization Ability Bug Finder [4, 15] Camera Detector [7, 8, 18] mmWave Sensing (E-Eye) [41] Network Traffic at Router [45,48,53] Camera Detection w 802.11 Packets [26, 42] Lumos Table 1: Comparing existing approaches vs. Lumos Identifying diverse devices with limited features: Prior work associates IoT devices with signatures using higherlayer information IP, DNS, port numbers, and NTP protocols (e.g., [45, 53] ). However, due to limited network visibility, we can only observe 802.11 headers with coarse attributes. To address these issues, we design a systematic machine learning (ML) framework, which considers a broad observable feature set, rather than handcrafted features [45, 53] , both temporally and across packet header attributes. To tackle device diversity, we use multiple timescales in feature engineering to extract device-specific attributes. This allows us to generalize across a large set of device types from different vendors and with different hardware settings.