This repository contains the code implementation for the paper titled "A Practical Deep Learning-Based Acoustic Side Channel Attack on Keyboards".
With the advancements in deep learning, the widespread use of microphones, and the increasing reliance on online services through personal devices, the vulnerability of keyboards to acoustic side channel attacks has become a significant concern. In this paper, we present a practical implementation of a state-of-the-art deep learning model that classifies laptop keystrokes using a smartphone integrated microphone. Our trained classifier achieved an accuracy of 95% when trained on keystrokes recorded by a nearby phone, which is the highest accuracy achieved without the use of a language model. Furthermore, when trained on keystrokes recorded using the video-conferencing software Zoom, an accuracy of 93% was achieved, setting a new benchmark in this domain. These results highlight the feasibility of side channel attacks employing off-the-shelf equipment and algorithms. We also propose several mitigation methods to safeguard users against such attacks.
The full paper can be accessed here
- Acoustic side channel attack
- Deep learning
- User security and privacy
- Laptop keystroke attacks
- Zoom-based acoustic attacks
Please refer to the paper for detailed information and methodology.