Generative adversarial network produces a "universal fingerprint" that will unlock many smartphones / Boing Boing
Researchers at NYU and U Michigan have published a paper explaining how they used a pair of machine-learning systems to develop a "universal fingerprint" that can fool the lowest-security fingerprint sensors 76% of the time (it is less effective against higher-security sensors). The researchers used "generative adversarial networks" (GAN) to develop their attack. It is a technology I came across while researching for [Ganbreeder](https://steemhunt.com/@vimukthi/ganbreeder-otherworldly-artwork-generated-through-machine-learning)which generate artwork using Machine Learning.
Smartphones generally operate at the second tier of security, in which they are expected to generate false positives 0.1% of the time; and at this level, the researchers were able to spoof the sensors 22% of the time.
Recent research has demonstrated the vulnerability of fingerprint recognition systems to dictionary attacks based on MasterPrints. MasterPrints are real or synthetic fingerprints that can fortuitously match with a large number of fingerprints thereby undermining the security afforded by fingerprint systems.
Source of shared Link
I'm not at all surprised by this. Finger prints are now the least secure form of biometrics that can be used for unlocking encrypted data. Soon, fingerprints won't be able to be used for security at all, and systems will have to move to using more advanced things, such as the Face ID system on iPhones, or the newer technology of scanning the veins in a persons hand. In theory, it could eventually reach the point of requiring actual DNA for very high-security purposes.
Very true. The biggest problem is not really the fingerprinting but the scanners. It's a "cool" feature to have. But not enough attention is given to quality. Face ID at least have high quality cameras at this point after constant innovation. But fingerprin scanners on mibile devices is mostly just a gimmick. We can still work this out. But we need more sensitive and refined scanners.
Yeah, finger print scanners are ok on mobile devices for day-to-day usage, but not for storing classified secrets. And even then, the day-to-day use won't be secure enough with it either. And to be honest, Face ID is just more intuitive than the Fingerprint unlock... :3
Defended (62.21%)
Summoned by @vimukthi
Sneaky Ninja supports @youarehope and @tarc with a percentage of all bids.
Everything You Need To Know About Sneaky Ninja
woosh