26 May 2020 in IEEE Internet of Things Journal
Internet of Things is a critical infrastructure component as well as an enabling technology to support the fast-developing cross-region, cross-application, and diversified collaborative smart city services that require systematic cooperation among multiple smart city systems. Speech recognition-based voice controllable systems become one of the most popular interfaces in smart devices. However, it has been proved that attackers can hide their voice commands via modulating them on ultrasonic carriers and carry out inaudible voice attacks to manipulate voice controllable devices (e.g., mobile phone) unnoticeably. Although there are defense suggestions to enhance the hardware or add new modules of microphones, it is impractical to change the hardware design of all voice-controllable devices developed by different manufactures. In this article, we validate the effectiveness of ultrasonic-based inaudible voice attacks to voice-controllable smart home devices and propose a signal-processing-based hidden voice attack detection approach. Our approach uses an independent device that deploys a two-step lightweight detecting algorithm to identify the attack signals. We simulate our algorithm and make a prototype implementation of the proposed approach. The simulation results illustrate the correctness of the detection algorithm and the experiments show that our approach can detect the ultrasonic-based inaudible voice attack effectively.
1 January 2022 in Wireless Communications and Mobile Computing
As a typical application of Internet of Things (IoT), home automation systems, namely, smart homes, provide a more convenient and intelligent life experience through event recognition, automation control, and remote device access. However, smart home systems have also given rise to new complications for security issues. As an event‐driven IoT system, smart home environments are vulnerable to security attacks, and vulnerable devices are far‐spread due to the quick development cycles. Attack vectors to smart homes inevitably manifest in abnormal event contexts. In this paper, we propose HomeGuardian, a context‐based approach to identify abnormal events in smart homes. In our approach, we extract temporal context and environmental context from system logs, aggregate (embed) these hybrid contexts, and construct a learning‐based classifier to identify the abnormal events. We develop a testbed to implement and evaluate our approach.