Using Artificial Intelligence to Confuse Hackers: Introducing WE-FORGE

Information Fabricated

This post is available in Hebrew: bryt

Hackers are constantly improving their ability to penetrate cyber defenses and steal valuable documents. So some researchers propose using an artificial-intelligence algorithm to hopelessly confuse them, once they break-in, by hiding the real deal amid a mountain of convincing fakes. The algorithm is called Word Embedding based Fake Online Repository Generation Engine, or WE-FORGE. It generates fake patents that are in development. Subrahmanian, a Dartmouth College cybersecurity expert and the algorithm’s developer, says that it will eventually \”create a large number of fake versions of all documents that a business feels it must protect\”.

Hackers who wanted to steal a formula, for example, would need to sift through a large number of fakes. This might mean carefully checking every formula, and perhaps investing in some dead-end recipes. Subrahmanian says, \”The goal is to make it harder.\” \”Inflict pain to those who steal from you.\”