I was reading this report: https://www.theverge.com/2017/4/12/15271874/ai-adversarial-images-fooling-attacks-artificial-intelligence

Researchers used noise to trick machine learning algorithms to misidentify or misclassify an image of a fish as a cat. I was wondering if something like that can be used to create subliminals.

What I mean by subliminals: United Nations has defined subliminal messages as perceiving messages without being aware of them, it is unconscious perception, or perception without awareness. Like you may be aware of a message but cannot consciously perceive that message in the form of text, etc.

All the reports about the noise trick said the noise was so transparent that humans couldn't detect it. This can be changed to make it noticeable unconsciously but unnoticeable at a conscious level so a human can register the subliminal but not be aware of it.

Is it possible to take an output from a hidden layer to construct such subliminal for humans, with trial and error one can find right combination? Can it be possible to come up with a pixel pattern or noise with ML which allows one to impose subliminals?

  • 2
    $\begingroup$ Basically, subliminal images are a set of images that we can perceive unconsciously but not consciously. There are some speculations whether certain companies have used such images in their advertising campaigns. To my best of understanding, OP is asking whether ML is every involved or can be involved, to create images that exhibit such property. $\endgroup$ – SpiderRico Jun 15 at 1:12

I would say no, at least not now. To achieve that you need to have a model that represents the structure of a human brain at a very detailed level, so that inherits the same flaws.

| improve this answer | |
  • $\begingroup$ I'm wondering if a knowledge of how neurons process and function in computer vision can be enough to create something like that, like when scrolling up and down, or seeing static or moving images. So you are basically saying someone with enough computation power like Google, Microsoft, CIA would be able to do it because they use neurologists everyday. $\endgroup$ – noviceFedora Jun 14 at 23:40
  • $\begingroup$ I do not think that we understand how human brain operates, so only a lucky guess can occur. $\endgroup$ – oleg.mosalov Jun 16 at 8:53

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.