Poster: Acoustic Side-Channel Attack on Robot Vacuums

Robot vacuums have become a ubiquitous appliance, offering un- paralleled convenience and efficiency in maintaining cleanliness in both residential and commercial spaces. However, these devices also present a convenient method for attackers to gather information about the robot's surroundings. In this study, we investigate the feasibility of acoustic side-channel attacks on robot vacuums and demonstrate that sensitive information can be easily obtained by analyzing the sound produced by the robot. We extract various characteristic features and spectrograms from the sound emitted during robot movement and classify them using Multilayer Perception and Convolutional Neural Network. The evaluation results demonstrate the effectiveness of the acoustic attacks, with both machine learning models achieving more than 95% accuracy in classifying the robot's movement based on acoustic signals. Using our ML model, we demonstrate that robot cleaning path can be effectively identified with 96% accuracy. To mitigate such a threat, we perform a simulation where random noise is added to the sound samples, which effectively reduce the motion identification accuracy to 43%.