When Vision Fails: Text Attacks Against ViT and OCR

1 code implementation • 12 Jun 2023 • Nicholas Boucher, Jenny Blessing, Ilia Shumailov, Ross Anderson, Nicolas Papernot

While text-based machine learning models that operate on visual inputs of rendered text have become robust against a wide range of existing attacks, we show that they are still vulnerable to visual adversarial examples encoded as text.

Optical Character Recognition (OCR)