Jailbreaking LLMs with Arabic Transliteration and Arabizi

Mansour Ghanim, Saleh Almohaimeed, Mengxin Zheng, Yan Solihin, Qian Lou


Abstract
This study identifies the potential vulnerabilities of Large Language Models (LLMs) to ‘jailbreak’ attacks, specifically focusing on the Arabic language and its various forms. While most research has concentrated on English-based prompt manipulation, our investigation broadens the scope to investigate the Arabic language. We initially tested the AdvBench benchmark in Standardized Arabic, finding that even with prompt manipulation techniques like prefix injection, it was insufficient to provoke LLMs into generating unsafe content. However, when using Arabic transliteration and chatspeak (or arabizi), we found that unsafe content could be produced on platforms like OpenAI GPT-4 and Anthropic Claude 3 Sonnet. Our findings suggest that using Arabic and its various forms could expose information that might remain hidden, potentially increasing the risk of jailbreak attacks. We hypothesize that this exposure could be due to the model’s learned connection to specific words, highlighting the need for more comprehensive safety training across all language forms.
Anthology ID:
2024.emnlp-main.1034
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
18584–18600
Language:
URL:
https://aclanthology.org/2024.emnlp-main.1034
DOI:
Bibkey:
Cite (ACL):
Mansour Ghanim, Saleh Almohaimeed, Mengxin Zheng, Yan Solihin, and Qian Lou. 2024. Jailbreaking LLMs with Arabic Transliteration and Arabizi. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 18584–18600, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Jailbreaking LLMs with Arabic Transliteration and Arabizi (Ghanim et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.1034.pdf
Software:
 2024.emnlp-main.1034.software.zip
Data:
 2024.emnlp-main.1034.data.zip