Researchers have taught a neural network to deceive facial recognition systems installed in public
The new development identifies those parts of the facewhich are most often read by the facial recognition system, then it selects a special makeup that will help deceive the system. Then this makeup is applied to the person: as a result, the accuracy of the facial recognition system decreases from 47.5% to 1.2%
The neural network works in several stages and works with two models for facial recognition:
- own (it is also called surrogate).
- target (to be fooled).
First, the algorithm reads several photosperson and random people of the same sex. The algorithm then creates a heat map that shows the main areas that are the hallmarks of a particular person.
Next, a new face with makeup is created based on the heatmap. He is again passed through the recognition system until it ceases to recognize the person. After that, the resulting makeup can be applied.
The authors note that their development not only deceives recognition systems, but is also invisible to people, since the makeup turns out to be ordinary and does not stand out from the crowd.
Read more:
Astronomers accidentally find two galaxies at the edge of space and time
People first descended to the bottom of the "Hell's Well": what did they find there
Chinese jet drone flies a record 20 hours at a speed of 800 km / h