Aspects of the disclosure relate to monitoring virtual desktops accessed by devices at remote locations using machine-learning models to mitigate potential cyber-attacks. In some embodiments, a computing platform may monitor data associated with a series of activities from a virtual desktop accessed by a remote computing device. Subsequently, the computing platform may detect new activity data on the virtual desktop accessed by the remote computing device, and evaluate the new activity data relative to the data associated with the series of activities, wherein evaluating includes applying a machine learning model to the new activity data. Based on evaluating the new activity data, the computing platform may determine if the new activity data is indicative of a potential cyber-attack. In response to determining that the new activity data is indicative of a potential cyber-attack, the computing platform may initiate one or more security response actions.