Paper ID: 2402.03171

Homograph Attacks on Maghreb Sentiment Analyzers

Fatima Zahra Qachfar, Rakesh M. Verma

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.

Submitted: Feb 5, 2024