mlsanityData to 7 Oct 2026

Jailbreaking LLMs with Arabic Transliteration and Arabizi

arXiv 2406.18725 ↗First posted 26 Jun 2024cs.LG cs.CLcited by 7

On the map: LLM safety and security → Jailbreaking

Abstract (arXiv)

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.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Placed in Jailbreaking, one of 12 directions in LLM safety and security. Builds on 23 of its 53 references that are in the map. First posted on arXiv 26 Jun 2024.

Builds on

23 of 53 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs8 Feb
  2. 2023Low-Resource Languages Jailbreak GPT-43 Oct
  3. 2023GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher12 Aug
  4. 2023Universal and Transferable Adversarial Attacks on Aligned Language Models27 Jul
  5. 2023Jailbroken: How Does LLM Safety Training Fail?5 Jul
  6. 2023Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study23 May

Other references · 17

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,854
  5. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  6. 2017Deep reinforcement learning from human preferencescited by 3,846
  7. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,308
  8. 2023Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!cited by 1,106
  9. 2019Universal Adversarial Triggers for Attacking and Analyzing NLPcited by 709
  10. 2023Shadow Alignment: The Ease of Subverting Safely-Aligned Language Modelscited by 284
  11. 2023Generative Language Models and Automated Influence Operations: Emerging Threats and Potential Mitigationscited by 157
  12. 2018Improving Automatic Source Code Summarization via Deep Reinforcement Learningcited by 99
5 more
  1. 2022Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Modelscited by 67
  2. 2023The Next Chapter: A Study of Large Language Models in Storytellingcited by 58
  3. 2023TrojText: Test-time Invisible Textual Trojan Insertioncited by 26
  4. 2024AraTrust: An Evaluation of Trustworthiness for LLMs in Arabiccited by 16
  5. 2023TrojFSP: Trojan Insertion in Few-shot Prompt Tuningcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 5; 2026: 1.

7 papers.

  1. 2025The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating Itcited by 42
  2. 2025Enhancing Jailbreak Attacks on LLMs via Persona Promptscited by 10
  3. 2025Three Minds, One Legend: Jailbreak Large Reasoning Model with Adaptive Stacked Cipherscited by 8
  4. 2025Guarding the Guardrails: A Taxonomy-Driven Approach to Jailbreak Detectioncited by 4
  5. 2024Data Defenses Against Large Language Modelscited by 2
  6. 2025TestDG: Test-time Domain Generalization for Continual Test-time Adaptationcited by 0
  7. 2026Devling into Adversarial Transferability on Image Classification: Review, Benchmark, and Evaluationcited by 0