Enabling permissible interactions with applications shared during audio-visual communication sessions

A method comprising:

• identifying parameter data associated with an application;
• detecting an interaction with a portion of the application;
• receiving or generating a dataset comprising a plurality of entries for a plurality of interactions;
• inputting, into a machine learning model, the dataset to obtain one or more predictions indicating one or more permissible interactions for the application, wherein the machine learning model has been trained to indicate whether interactions with portions of applications are permissible;
• determining, based on the one or more predictions, whether the interaction is permissible for the application;
• and
• performing an action based on determining whether the interaction is permissible for the application.

A non-transitory, computer-readable medium storing instructions that when executed by one or more processors cause the one or more processors to perform operations comprising:

• detecting an interaction with a shared application;
• receiving or generating a dataset comprising a plurality of entries for a plurality of interactions;
• inputting, into a machine learning model, the dataset to obtain information regarding one or more permissible interactions for the shared application;
• determining, based on inputting into the machine learning model, whether the interaction is permissible for the shared application;
• and
• performing an action based on determining whether the interaction is permissible for the shared application.