# Homograph Attacks on Maghreb Sentiment Analyzers

arXiv: https://arxiv.org/abs/2402.03171 · HTML: https://mlsanity.com/paper/2402.03171/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 1 of its 4 references that are in the map.
- First posted on arXiv 5 Feb 2024.

## Builds on (most cited first, 1 of 1)

- [TUNIZI: a Tunisian Arabizi sentiment analysis Dataset](https://mlsanity.com/paper/2004.14303/) (2020)

## Abstract (arXiv)

We examine the impact of homograph attacks on the Sentiment Analysis (SA) task of different Arabic dialects from the Maghreb North-African countries. Homograph attacks result in a 65.3% decrease in transformer classification from an F1-score of 0.95 to 0.33 when data is written in "Arabizi". The goal of this study is to highlight LLMs weaknesses' and to prioritize ethical and responsible Machine Learning.