News for hackers. Stuff that matters.
Re:Optical illusions that flummox computers by itchyjunk on Saturday April 15, 2017 @12:47PM (#14121521)
In nature, the natural neural network called brain seems to weigh in the information from multiple sources instead of relying on just one. Not just in terms of number of sense but even for the same sense. Vision for example: it gets input from 2 eyes and if the data between the two is too inconstant, it sometimes drops it.

The machine learning systems will probably use similar tricks at some point. You might need to double the resource needed to process data twice or more, but you end up with a harder to fool systems. At least with the current adversarial attacks.

------------------

[0] https://www.scientificamerican.com/article/two-eyes-two-view...

[1] http://www.bbc.com/future/bespoke/story/20150130-how-your-ey...

Re:Optical illusions that flummox computers by lisper on Saturday April 15, 2017 @03:21PM (#14122344)
Even the human brain often gets things catastrophically wrong. The problem is that it's only evident when it happens to other people, not so much when it happens to you. And if you're surrounded by people all of whom have the same bug in their wetware, then it gets really hard to tell.
Re:Optical illusions that flummox computers by craigching on Saturday April 15, 2017 @11:20PM (#14124162)
This is a really interesting avenue to explore. How easy is it for humans to misunderstand something such that it leads to "catastrophic" failures. Here, a catastrophic failure could be something as simple as a huge fight between two people for a simple misunderstanding. If humans can have "breakdowns" based on simple misunderstandings, what are the cascading effects from a simple misclassification that can happen?
Re:Optical illusions that flummox computers by lisper on Sunday April 16, 2017 @04:57PM (#14127469)
Re:Optical illusions that flummox computers by caseysoftware on Sunday April 16, 2017 @12:10AM (#14124274)
It happens with sound/words too: https://en.wikipedia.org/wiki/Mondegreen

Humans are bad at recognition but still the best there are.