AI Used To Create Synthetic Fingerprints, Fools Biometric Scanners

Fingerprint scanners have become pretty commonplace for use on smartphones and in some cases, even laptops. Given that we all have unique fingerprints, it makes sense that fingerprints are used as a form of biometric security, but unfortunately it seems that it might not be as secure as we think anymore.

This is according to recent research done by researchers from New York University where they have found (via Gizmodo) that AI can actually be used to generate a synthetic fingerprint that can actually fool biometric scanners. Dubbed the DeepMasterPrints, it seems that the system managed to replicate 23% of fingerprints within a system that supposedly has an error rate of one in a thousand.

This also takes advantage of the fact that most biometric systems don’t merge partial prints together to form a full image, and also the fact that when you scan your prints, only the surface touching the scanner is read. This means that through trial and error, these AI-generated prints could potentially be used by hackers to bypass a system, similar to how brute force attacks work when attempting to figure out a password.

Now before you get too worried about hackers using this system to bypass your phone’s fingerprint system, lead researcher Philip Bontrager said, “A similar setup to ours could be used for nefarious purposes, but it would likely not have the success rate we reported unless they optimized it for a smartphone system. This would take a lot of work to try and reverse engineer a system like that.” The researchers are also hoping that their work will prompt companies to come up with more secure systems in the future.

Tyler Lee
Categories: General
Tags: AI (Artificial Intelligence), Security