jm + deep-learning + classification   2

Fooling Neural Networks in the Physical World with 3D Adversarial Objects · labsix
This is amazingly weird stuff. Fooling NNs with adversarial objects:
Here is a 3D-printed turtle that is classified at every viewpoint as a “rifle” by Google’s InceptionV3 image classifier, whereas the unperturbed turtle is consistently classified as “turtle”.

We do this using a new algorithm for reliably producing adversarial examples that cause targeted misclassification under transformations like blur, rotation, zoom, or translation, and we use it to generate both 2D printouts and 3D models that fool a standard neural network at any angle. Our process works for arbitrary 3D models - not just turtles! We also made a baseball that classifies as an espresso at every angle! The examples still fool the neural network when we put them in front of semantically relevant backgrounds; for example, you’d never see a rifle underwater, or an espresso in a baseball mitt.
ai  deep-learning  3d-printing  objects  security  hacking  rifles  models  turtles  adversarial-classification  classification  google  inceptionv3  images  image-classification 
november 2017 by jm
When DNNs go wrong – adversarial examples and what we can learn from them
Excellent paper.
[The] results suggest that classifiers based on modern machine learning techniques, even those that obtain excellent performance on the test set, are not learning the true underlying concepts that determine the correct output label. Instead, these algorithms have built a Potemkin village that works well on naturally occuring data, but is exposed as a fake when one visits points in space that do not have high probability in the data distribution.
ai  deep-learning  dnns  neural-networks  adversarial-classification  classification  classifiers  machine-learning  papers 
february 2017 by jm

Copy this bookmark: