- cross-posted to:
- [email protected]
- [email protected]
- cross-posted to:
- [email protected]
- [email protected]
Hey koavf, I hope this is OK to post here! Let me know if you’d like me to take it down
Hey koavf, I hope this is OK to post here! Let me know if you’d like me to take it down
well, it’s rather the opposite - AI is vulnerable to these kinds of tricks, you can inject some patterns into images to make the AI perceive the image in a completely different way, humans are in fact much less susceptible to this, at least for now
So how does ai exactly knows which color is the picture… I always thought that by analysing the binary it is possible to recognize previous learned sequences for predetermined colors and as such answer the question… In this example there’s no sequence for red for example…
AI basically recognizes patterns and returns a likely output based on the patterns it found. It doesn’t check “this is a red pixel, so this is red”, it checks “this pattern is usually red, so this is red”.
And what about shapes that doesn’t have a default colour? For example an apple ? Red green yellow ? Or a bold number
It will come up with an answer at random or have bias based on the training data or one based on random chance.