Machine Learning Masters the Fingerprint to Fool Biometric Systems
Fingerprint authentication systems are a widely trusted, ubiquitous form of biometric authentication, deployed on billions of smartphones and other devices worldwide. Yet a new study from New York University Tandon School of Engineering reveals a surprising level of vulnerability in these systems. Using a neural network trained to synthesize human fingerprints, the research team evolved a fake fingerprint that could potentially fool a touch-based authentication system for up to one in five people.
Much the way that a master key can unlock every door in a building, these “DeepMasterPrints” use artificial intelligence to match a large number of prints stored in fingerprint databases and could thus theoretically unlock a large number of devices.
The research team was headed by NYU Tandon Associate Professor of Computer Science and Engineering Julian Togelius and doctoral student Philip Bontrager, the lead author of the paper, who presented it at the IEEE International Conference of Biometrics: Theory, Applications and Systems, where it won the Best Paper Award.
The work builds on earlier research led by Nasir Memon, professor of computer science and engineering and associate dean for online learning at NYU Tandon. Memon, who coined the term “MasterPrint,” described how fingerprint-based systems use partial fingerprints, rather than full ones, to confirm identity. Devices typically allow users to enroll several different finger images, and a match for any saved partial print is enough to confirm identity. Partial fingerprints are less likely to be unique than full prints, and Memon’s work demonstrated that enough similarities exist between partial prints to create MasterPrints capable of matching many stored partials in a database.
Bontrager and his collaborators, including Memon, took this concept further, training a machine-learning algorithm to generate synthetic fingerprints as MasterPrints. The researchers created complete images of these synthetic fingerprints, a process that has twofold significance. First, it is yet another step toward assessing the viability of MasterPrints against real devices, which the researchers have yet to test; and second, because these images replicate the quality of fingerprint images stored in fingerprint-accessible systems, they could potentially be used to launch a brute force attack against a secure cache of these images.
“Fingerprint-based authentication is still a strong way to protect a device or a system, but at this point, most systems don’t verify whether a fingerprint or other biometric is coming from a real person or a replica,” said Bontrager. “These experiments demonstrate the need for multi-factor authentication and should be a wake-up call for device manufacturers about the potential for artificial fingerprint attacks.”
This research has applications in fields beyond security. Togelius noted that their Latent Variable Evolution method used here to generate fingerprints can also be used to make designs in other industries — notably game development. The technique has already been used to generate new levels in popular video games
The Latest on: Synthetic fingerprints
via Google News
The Latest on: Synthetic fingerprints
- Galaxy S10 has an ultrasonic fingerprint scanner. Here's why you should care on February 21, 2019 at 2:42 pm
The ultrasonic sensor module can map out that data to form a detail-rich 3D image of your fingerprint. The soundwaves can also detect your blood flow, and would reject a print from a severed finger. I... […]
- The Xiaomi Mi 9 launches with the Qualcomm Snapdragon 855, 48MP camera, up to 12GB RAM, In-display Fingerprint Scanner, and more on February 20, 2019 at 12:33 am
Lastly, the device has a fifth-generation optical in-display fingerprint scanner which Xiaomi says is 25 ... We’re definitely looking forward to benchmarking it in synthetic and real-world tests. The ... […]
- Synthetic Bots, OaaS Part 2 on February 13, 2019 at 4:31 am
Integrating specific traits in synthetic images Every social media ... personal information for signing up and logging in, like a fingerprint or face, but this would certainly encounter the ... […]
- Researchers develop artificial fingerprints, claiming they could hack into a third of smartphones on December 30, 2018 at 10:15 pm
These are machine-learning methods that act as a kind of "masterkey" which, the researchers claim, have the potential to unlock around one in three fingerprint-protected smartphones. In the paper rele... […]
- Machine learning masters the fingerprint to fool biometric systems on December 3, 2018 at 4:04 pm
The researchers created complete images of these synthetic fingerprints, a process that has twofold significance. First, it is yet another step toward assessing the viability of MasterPrints against r... […]
- AI-generated fingerprints could soon fool biometric systems on November 28, 2018 at 7:52 pm
Recently, researchers built upon these findings to create a new machine-learning algorithm that generates synthetic fingerprints. These AI-generated fakes could be pitted against real devices in the n... […]
- Think your devices are safe? New AI tool can fake fingerprints and fool biometric systems on November 26, 2018 at 8:15 pm
Researchers are training a machine-learning algorithm to generate synthetic fingerprints as MasterPrints.PTI | November 27, 2018, 09:41 IST NEW YORK: Scientists have developed an artificial intelligen... […]
- AI generates fake fingerprints to fool biometric systems on November 25, 2018 at 10:29 pm
Researchers took this concept further, training a machine-learning algorithm to generate synthetic fingerprints as MasterPrints. "Fingerprint-based authentication is still a strong way to protect a de... […]
- DeepMasterPrints fake fingerprints can fool fingerprint sensors on November 21, 2018 at 10:08 am
"This is the first work that creates a synthetic MasterPrint at the image level, thereby further reinforcing the danger of utilizing small-sized sensors with limited resolution in fingerprint applicat... […]
via Bing News