Smart home devices are vulnerable to passive inference attacks based on network traffic, even in the presence of encryption. In this paper, we present PingPong, a tool that can automatically extract packet-level signatures for device events (e.g., light bulb turning ON/OFF) from network traffic. We evaluated PingPong on popular smart home devices ranging from smart plugs and thermostats to cameras, voice-activated devices, and smart TVs. We were able to: (1) automatically extract previously unknown signatures that consist of simple sequences of packet lengths and directions; (2) use those signatures to detect the devices or specific events with an average recall of more than 97%; (3) show that the signatures are unique among hundreds of millions of packets of real world network traffic; (4) show that our methodology is also applicable to publicly available datasets; and (5) demonstrate its robustness in different settings: events triggered by local and remote smartphones, as well as by home-automation systems.
- R. Trimananda, J. Varmarken, A. Markopoulou, B. Demsky, “Packet-Level Signatures for Smart Home Devices,” in Proceedings of the 2020 Network and Distributed System Security Symposium (NDSS). February 2020, San Diego, CA.
- R. Trimananda, J. Varmarken, A. Markopoulou, and B. Demsky. Ping-pong: Packet-level signatures for smart home device events. http://arxiv.org/abs/1907.11797.
- Rahmadi Trimananda (UC Irvine, Programming Languages Research Group)
- Janus Varmarken (UC Irvine, Networking Group)
- Athina Markopoulou (UC Irvine, Networking Group)
- Brian Demsky (UC Irvine, Programming Languages Research Group)
Software and Dataset
- Software: please refer to the PingPong project page at the Programming Languages Research Group’s website to access the PingPong software.
- Dataset: please refer to this page to request access to the PingPong dataset.