Homograph Attacks on Maghreb Sentiment Analyzers

Authors: Fatima Zahra Qachfar, Rakesh M. Verma
Published: 2024-02-05

Source: https://arxiv.org/abs/2402.03171

PDF: https://arxiv.org/pdf/2402.03171

Labels Predicted by AI

LLMセキュリティ データセット生成 モデル性能評価

Please note that these labels were automatically added by AI. Therefore, they may not be entirely accurate.
For more details, please see the About the Literature Database page.

Abstract

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 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.