Search Results for author: Nicholas Boucher

Found 3 papers, 3 papers with code

When Vision Fails: Text Attacks Against ViT and OCR

1 code implementation12 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)

Boosting Big Brother: Attacking Search Engines with Encodings

1 code implementation27 Apr 2023 Nicholas Boucher, Luca Pajola, Ilia Shumailov, Ross Anderson, Mauro Conti

Search engines are vulnerable to attacks against indexing and searching via text encoding manipulation.

Chatbot Text Summarization

Bad Characters: Imperceptible NLP Attacks

1 code implementation18 Jun 2021 Nicholas Boucher, Ilia Shumailov, Ross Anderson, Nicolas Papernot

In this paper, we explore a large class of adversarial examples that can be used to attack text-based models in a black-box setting without making any human-perceptible visual modification to inputs.

Machine Translation

Cannot find the paper you are looking for? You can Submit a new open access paper.