U.S. Spies Want To Know How To Identify Compromised AI

The U.S. government’s research arm for intelligence organizations, IARPA, is looking for ideas on how to detect “Trojan” attacks on artificial intelligence, according to government procurement documents. Here’s the problem the agency wants to solve: At a simple level, modern image-recognition AI learns from analyzing many images of an object. If you want to train an algorithm to detect pictures of road signs, you have to supply it with pictures of different signs from all different angles. The algorithm learns the relationships between the pixels of the images, and how the structures and patterns of stop signs differ from those of speed-limit signs.