Technology giant Google and the University of Wisconsin-Madison have collaborated to develop a novel artificial intelligence (AI)-powered tool called CookieEnforcer that automatically disables unnecessary cookies.
The new AI tool can considerably help users browse the internet, eliminating the distraction caused by cookie consent pop-ups.
CookieEnforcer examines cookie alerts and predicts the steps necessary to remove all unneeded cookies. The AI tool has been developed to prevent cookies from persuading consumers to make website-friendly decisions that jeopardize their privacy.
The developers of CookieEnforcer said that the tool was determined to be 91 percent effective at automatically deactivating non-essential cookies when tested on the top 500 websites in the Tranco ranking list.
“We describe CookieEnforcer, a cookie enforcement controller system, which automatically finds cookie notices, locates the fine-grained options within these notices, understands the semantics of the cookies, and automatically disables non-essential cookies,” mentioned the researchers.
CookieEnforcer scans the domain and uses a machine-learning classifier to identify the cookie notice based on its textual and graphical features. It then interacts with every UI element on the notice to simulate user activity. Lastly, the researchers developed a decision model that uses the text associated with all cookie settings and their current state (selected or not-selected) to decide the actions needed to disable the unwanted cookies.
“This is done by modeling the problem as a sequence-to-sequence task, where the input is a machine-readable cookie notice, and the output is the set of clicks to make,” added the researchers.
As of now, CookieEnforcer has not been launched officially for public use, but the team plans to integrate the tool as a browser extension soon.