Artificial neural networks are computer programs that try to approximate what the human brain does to solve problems like recognizing objects in images. In this piece of work, the authors analyze the properties of these neural networks and try to unveil what exactly makes them think that a paper towel is a paper towel, and, building on this knowledge, try to fool these programs. Carefully crafted adversarial examples can be used to fool deep neural network reliably.
_______________
The paper “Intriguing properties of neural networks” is available here:
The paper “Explaining and Harnessing Adversarial Examples” is available here:
Image credits:
Thumbnail image – (CC BY-SA 2.0)
Shower cap – Code Words / Julia Evans –
MNIST – hxhl95
Andrej Karpathy’s online convolutional neural network:
Subscribe if you would like to see more of these! –
Splash screen/thumbnail design: Felícia Fehér –
Károly Zsolnai-Fehér’s links:
Patreon →
Facebook →
Twitter →
Web →
source