Artificial intelligence can make fake fingerprints that function as "masters" or the main keys for cellphones that use biometric sensors. According to security researchers who developed this technique, attacks can be launched against individual users with a certain percentage of performance.
In recent years, researchers have been able to prove and demonstrate that a large number of biometric security formats can be overwhelmed through biometric ID systems (print sensors, eye protection or even veins at hand). In most cases, biometric identification requires the making of photocopies of fake diagrams or facial scans that are appropriate to the individual. However, researchers from the University of New York and Michigan announced details about how it is possible to train machine learning algorithms that produce fake fingerprints, which serve as the basis for a large number of correct prints stored in the database.
Known as DeepMasterPrints, these artificially made prints are similar to the main keys in the building. Although the researchers mentioned were not the first to consider making the primary fingerprint, they were the first to make a functional version using the machine learning algorithm. This mold is specifically designed to target the type of fingerprint sensor that can be found on a cellphone.
Researchers showed that at the highest level of security, master prints were "not very good" in sensing the sensors, when they managed to trick the sensor for less than 1.2 percent of the road.
The study did not announce the end of the fingerprint identification system, but the researchers suggested that such biometric protection designers need to review solutions and determine compromises between the benefits offered by fingerprints and overall security in the future.
You can also track Benchmarks on social networks Facebook | Twitter | Instagram | YouTube |
Na Benchmark Forum You can always participate in current quality discussions from the IT industry