Improved Practical Vulnerability Analysis of Mouse Data According to Offensive Security based on Machine Learning in Image-Based User Authentication

Kyungroul Lee, Sun-Young Lee
2020 Entropy  
The objective of this study was to verify the feasibility of mouse data exposure by deriving features to improve the accuracy of a mouse data attack technique using machine learning models. To improve the accuracy, the feature appearing between the mouse coordinates input from the user was analyzed, which is defined as a feature for machine learning models to derive a method of improving the accuracy. As a result, we found a feature where the distance between the coordinates is concentrated in
more » ... specific range. We verified that the mouse data is apt to being stolen more accurately when the distance is used as a feature. An accuracy of over 99% was achieved, which means that the proposed method almost completely classifies the mouse data input from the user and the mouse data generated by the defender.
doi:10.3390/e22030355 pmid:33286129 pmcid:PMC7516828 fatcat:2ezmssol55avxkv6on5ttzdywq