User Tools

Site Tools


blit

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

blit [2019-12-05 01:28:52] (current)
Line 1: Line 1:
 +====== Towards computing a BLIT ======
  
 +Recent research in artificial neural networks shows how to generate adversarial examples - slightly perturbed images that cause complete misclassification or other failures of the model. Is it possible to generate images that will cause surprising effects in biological neural networks?
 +
 +Optical illusions and camouflage (both evolved and man-made) can be regarded as this.
 +
 +  * [[https://​www.biorxiv.org/​content/​10.1101/​461525v1|Neural Population Control via Deep Image Synthesis]] - pretrained AlexNet is used to approximate first three layers of V4 center of a macaque; an adversarial example is then generated using this model (with gradient ascent and random translations) with the goal to activate a chosen site (a few neurons around the electrode) and deactivate the others. And it works.
 +  * [[http://​perceive.dieei.unict.it/​deep_learning_human_mind.php|Deep Learning Human Mind for Automated Visual Classification]] - using RNN to classify EEG traces of human viewing ImageNet images. Maybe this could be used to create a (terrible) differentiable model (which makes producing adversarial examples a lot easier) even with common non-invasive EEG. Unfortunately the study seems to have sloppy statistics of the validation data.
 +    * [[https://​www.ncbi.nlm.nih.gov/​pmc/​articles/​PMC4546653/​|This paper]] presents worse results (but still significant) but seems to have correct experimental settings.
 +  * [[https://​keenlab.tencent.com/​en/​whitepapers/​Experimental_Security_Research_of_Tesla_Autopilot.pdf|Experimental Security Research of Tesla Autopilot]] - generating adversarial examples for a costly (1 inference/​second) blackbox (we don't know the gradient) model.
 +  * [[https://​arxiv.org/​abs/​1707.07397|Synthesizing Robust Adversarial Examples]] - generating adversarial objects when we can't control how pixels of our example get mapped to the network input (translation,​ rotation, perspective). They have even 3D-printed a physical object that causes misclassifications of photos where it is present.
 +  * [[https://​en.wikipedia.org/​wiki/​Trypophobia|Trypophobia]] „is an aversion to the sight of irregular patterns or clusters of small holes, or bumps.“ - apparently reaction to specific patterns is hardcoded (by evolutionary selection - predators, parasites?) in people
 +    * [[https://​www.kaggle.com/​cytadela8/​trypophobia|There is a Kaggle for that!]]
 +
 +===== Name of this page…? =====
 +
 +[[https://​en.wikipedia.org/​wiki/​BLIT_(short_story)|BLIT]] is a concept from science-fiction,​ an image which triggers seizures (or even death) in people. In reality, we have [[https://​en.wikipedia.org/​wiki/​Denn%C5%8D_Senshi_Porygon#​Strobe_lights|video sequences]] that rarely trigger epilepsy, though. (now, optimize the function "how big unusual EEG patterns are caused when viewing such video"​)
 +
 +===== Possible uses =====
 +
 +  * fun&​trolling
 +  * advertisements exploiting bugs in human brain
 +  * biological warfare
blit.txt · Last modified: 2019-12-05 01:28:52 (external edit)