New Method Enables AI Models to Forget Private and Copyrighted Data

New method enables AI models to forget private and copyrighted data

A team of computer scientists at UC Riverside has developed a method to erase private and copyrighted data from artificial intelligence models—without needing access to the original training data.

New method enables AI models to forget private and copyrighted data – Tech Xplore – OPUS IP

New method enables AI models to forget private and copyrighted data  Tech Xplore

UC Riverside Leads the Charge in Eliminating Private Data from AI Models

A groundbreaking development in artificial intelligence has emerged from the University of California, Riverside (UCR), where a team of researchers has pioneered a method that allows AI models to “forget” specific private or copyrighted information without requiring access to the original training data. This significant technological advancement addresses the critical issue of data privacy and intellectual property rights in the age of AI, where…