News for hackers. Stuff that matters.
Re:Toyotas Unintended Acceleration and the Big Bowl of “Spag... by rainforest on Tuesday June 02, 2015 @04:26AM (#9644587)
Given that a lot of computer vision work is based on randomised algorithms, do you think that these standards would be enough? You could demonstrate 100% MC/DC coverage through a neural net implementation, but the weights are where the faults probably exist, for example.
Re:Toyotas Unintended Acceleration and the Big Bowl of “Spag... by mtrimpe on Tuesday June 02, 2015 @06:30AM (#9644960)
That actually leads to a very interesting point; would self driving cars be vulnerable to adversarial imagery?

Neural nets are well known for being easily fooled [1] ... I wonder if you could create similar situations for self-driving cars.

[1] http://www.evolvingai.org/fooling