papers in adversarial machine learning — adversarial attack

Adversarial patches showed a lot promise in 2017 for confusing object detection algorithms -- by making bananas look like a toaster. But what if you want the bananas to disappear? This blog post summarizes a 2019 paper showing how an adversarial patch can conduct an evasion attack, to avoid detection at all.

Adding small pixel changes won't be a successful adversarial attack in real life, because those changes get lost in lighting/shadows/dust on the camera lens. A newer technique -- adversarial patches -- provides a method for fooling object detection algorithms that are deployed in the real world.

You might not be aware of something very interesting -- that the big fancy neural networks that companies like Google and Facebook use inside their products are actually quite easy to fool. Here's how it works.