How hackers can force AI to make dumb mstakes

https://www.dailydot.com/debug/adversarial-attacks-ai-mistakes/

...

For instance, in 2016, researchers at Carnegie Mellon University showed that by donning special glasses, they could fool face-recognition algorithms to mistake them for celebrities they certainly did not look like. 

.......

"Deep neural networks[DNNs] overachieve at tasks that can be performed by humans, giving the impression that they have a higher understanding than we do," says Sridhar Muppidi, CTO at IBM Security. In practice, however, DNNs aim to simulate human behavior while having a completely different internal decision process composed of mathematical functions. 

..............