Going Undercover

If you’re nervous about facial recognition software tracking your movements, it turns out the latest countermove is in your cosmetics shop:

Face recognition algorithms can be foiled by a dab of strategically applied make-up that is subtle enough not to draw human attention.

Face recognition software is used in smartphones and similar technology – and also by the police. As such, there is interest in finding ways to fool the system.

Nitzan Guetta at Ben-Gurion University of the Negev in Israel and colleagues have developed AI software that can suggest where to apply make-up to trick face recognition systems into thinking a person’s identity has changed.

Tested against real-world face recognition technology, make-up applied according to the recommendations of the software could foil the system 98.8 per cent of the time. Across all people, the face recognition software could identify someone successfully 47.6 per cent of the time, but this dropped to 1.2 per cent with the make-up applied. [NewScientist (2 October 2021, paywall)]

That’s an amazing number, and more are cited. If true, it suggests that such ML (machine learning) algorithms are still terribly brittle and, therefore, relatively useless outside of strictly limited domains.

And the thought of a facial database containing dozens or hundreds of unconnected versions of me amuses me obscurely.

However …

Tested on 10 men and 10 women aged 20 to 28, wearing the make-up dropped the face recognition success rate from 42.6 per cent to 0.9 per cent in women and from 52.5 per cent to 1.5 per cent in men.

Gimme a break! That’s hardly a dispositive study size, now is it?

Bookmark the permalink.

About Hue White

Former BBS operator; software engineer; cat lackey.

Comments are closed.