How to confuse Artificial Intelligence

There was a lot of excitement last week sbout fooling AI image recognition by changing 1 pixel:
https://www.theregister.co.uk/2017/10/30/fool_ai_image_classifier_by_changing_single_pixel/
as in the title image from arXiv:1710.08864  [really about 0.1% of pixels]

This study goes a bit further to criticize probability theory and underlying statistical assumptions:
https://medium.com/intuitionmachine/why-probability-theory-should-be-thrown-under-the-bus-36e5d69a34c9

A starting point is this animated gif and study showing different graphs with the same statistical characteristics:
https://www.autodeskresearch.com/publications/samestats

Same Stats, Different Graphs: Generating Datasets with Varied Appearance and Identical Statistics through Simulated Annealing

 

However what humans call Common Sense isn’t just fine tuning of one algorithm, it’s a comparison of different algorithms and sensory inputs to cross-check the result.

Or to put it another way: If it looks like a duck, swims like a duck, and quacks like a duck, then it probably is a duck.
If we only hear a quack, we can’t be sure.

Advertisements

One thought on “How to confuse Artificial Intelligence

  1. On further investigation, actually google wrote a paper on this in 2015, showing for example that by applying only a 4% adjustment, this panda could be recognised as a Gibbon…
    Panda to Gibbon

    A good summary here.

    The one-pixel attack sounds new and sensational but is based on a very low number of pixels. On the other hand many exercises due use a very low number of pixels..

    Like

Leave a Reply

Please log in using one of these methods to post your comment:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s