PingPong: Packet-Level Signatures for Smart Home Device Events

07/26/2019
by   Rahmadi Trimananda, et al.
0

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 (i.e., simple sequences of packet lengths and directions) from the network traffic of smart home devices, and use those signatures to detect occurrences of specific device events (e.g., light bulb turning ON/OFF). We evaluated PingPong on popular smart home devices ranging from smart plugs to thermostats and home security systems. We have successfully: (1) extracted packet-level signatures from 18 devices (11 of which are the most popular smart home devices on Amazon) from 15 popular vendors, (2) used those signatures to detect occurrences of specific device events with an average recall of more than 97 that the signatures are unique among tens of millions of packets of real world network traffic.

READ FULL TEXT

page 4

page 7

page 11

research
07/22/2021

ZLeaks: Passive Inference Attacks on Zigbee based Smart Homes

In this work, we analyze the privacy guarantees of Zigbee protocol, an e...
research
07/27/2017

Runtime Model Based Approach to Smart Home System Development

When developing smart home systems, developers integrate and compose sma...
research
09/01/2017

Inferring Networked Device Categories from Low-Level Activity Indicators

We study the problem of inferring the type of a networked device in a ho...
research
09/16/2020

The Dark (and Bright) Side of IoT: Attacks and Countermeasures to Identification of Smart Home Devices and Services

We present a new machine learning-based attack that exploits network pat...
research
05/08/2023

Smart Home Device Detection Algorithm Based on FSA-YOLOv5

Smart home device detection is a critical aspect of human-computer inter...
research
03/24/2023

"Get ready for a party": Exploring smarter smart spaces with help from large language models

The right response to someone who says "get ready for a party" is deeply...
research
02/25/2021

Deep Adversarial Learning on Google Home devices

Smart speakers and voice-based virtual assistants are core components fo...

Please sign up or login with your details

Forgot password? Click here to reset