The inventor, U of A Associate Professor of computer science, Marcus Brown, remembers as a kid reading about Thomas Edison who, among other things, was a telegraph operator and that good telegraph operators could tell who was on the other side of the wire based on their exact patterns of dots and dashes.
Similarly, Brown's invention trains a neural network, a type of computer program that "learns" by example, using the precise time that each key is pressed and released by its user. Measured precisely enough, each person's typing pattern is a fingerprint of sorts, unique to them. It's unclear if this uniqueness relates to the physical structure of individuals' hands, the way they break up words mentally when they type them, or both.
Information security is a natural fit for the technology. The researchers say keystroke authentication won't replace passwords, but rather would add another layer of protection. Most information security is "brittle," in that a compromised password gives an interloper full access to potentially sensitive data. Companies are actively looking for ways to protect against such unauthorized access.