Online Traffic Obfuscation Experimental Framework for the Smart Home Privacy Protection

With the widespread adoption of smart home devices, users’ home behaviors are at risk of privacy leakage due to traffic analysis attacks. Attackers can use Ethernet or WiFi sniffers to capture device traffic and identify device events based on packet length and timing characteristics, thereby inferring users’ home behaviors. To address this issue, traffic obfuscation techniques have been extensively studied, with common methods including packet padding, packet segmentation, and fake traffic injection. However, existing research predominantly utilizes non-real-time traffic, such as simulated, offline, and replayed traffic, to verify whether traffic obfuscation techniques can effectively reduce the recognition rate of traffic analysis attacks on smart home devices. It often overlooks the potential impact of obfuscation operations on device connectivity and functional integrity in real network environments, which represents an inherent limitation of the experimental verification method using non-real-time traffic. To address this limitation, an online experimental framework for three fundamental traffic obfuscation techniques is proposed: packet padding, packet segmentation, and fake traffic injection. This framework ensures the continuous connectivity and functional integrity of smart home devices. The fundamental traffic obfuscation techniques implemented within the online experimental framework can only resist some of the existing traffic analysis methods; this is consistent with current research findings. Importantly, the proposed framework facilitates relevant researchers in extending these fundamental techniques to novel complex traffic obfuscation methods while continuously assessing the effectiveness of these methods online.