mlsanityData to 7 Oct 2026

Homograph Attacks on Maghreb Sentiment Analyzers

arXiv 2402.03171 ↗First posted 5 Feb 2024cs.CL cs.CR cs.LGcited by 0

Not on the map. Why?

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 1 of its 4 references that are in the map. First posted on arXiv 5 Feb 2024.

Builds on

1 of 4 references.

References · 1

  1. 2020TUNIZI: a Tunisian Arabizi sentiment analysis Datasetcited by 11

Built on by

Not cited yet.