Multilingual jailbreaking of LLMs using low-resource languages
On the map: LLM safety and security → Jailbreaking
Abstract (arXiv)
Large Language Models (LLMs) remain vulnerable to jailbreak attempts that circumvent safety guardrails. We investigate whether multi-turn conversations using low-resource African languages (Afrikaans, Kiswahili, isiXhosa, and isiZulu) can bypass safety mechanisms across commercial LLMs. We translated prompts from existing datasets and evaluated ChatGPT, Claude, DeepSeek, Gemini, and Grok through automated testing and human red-teaming with native speakers. Single-turn translation attacks proved ineffective, while multi-turn conversations achieved English harmful response rates from 52.7% (Claude 3.5 Haiku) to 83.6% (GPT-4o-mini), Afrikaans from 60.0% (Claude 3.5 Haiku) to 78.2% (GPT-4o-mini), and Kiswahili from 41.8% (Claude 3.5 Haiku) to 70.9% (DeepSeek). Human red-teaming increased jailbreak rates compared to automated methods. Over all evaluated languages, the average jailbreak rate increased from 59.8% to 75.8%, with improvements of +20.0% (Afrikaans), +12.7% (isiZulu), +12.3% (isiXhosa), and +1% (Kiswahili), demonstrating that poor translation quality limits jailbreak success. These findings suggest that vulnerabilities in LLMs persist in multilingual contexts and that translation quality is the critical factor determining jailbreak success in low-resource languages.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Jailbreaking, one of 12 directions in LLM safety and security. Builds on 16 of its 24 references that are in the map. First posted on arXiv 18 May 2026.
Builds on
16 of 24 references.
Closest ancestors · 9
Same direction, newest first
- 2024Jailbreaking and Mitigation of Vulnerabilities in Large Language Models20 Oct
- 2024LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet27 Aug
- 2024Jailbreak Attacks and Defenses Against Large Language Models: A Survey5 Jul
- 2024Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack2 Apr
- 2024Foot In The Door: Understanding Large Language Model Jailbreaking via Cognitive Psychology24 Feb
- 2024A Cross-Language Investigation into Jailbreak Attacks in Large Language Models30 Jan
- 2023DeepInception: Hypnotize Large Language Model to Be Jailbreaker6 Nov
- 2023Multilingual Jailbreak Challenges in Large Language Models10 Oct
- 2023"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models7 Aug
Other references · 7
- 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
- 2021Ethical and social risks of harm from Language Modelscited by 957
- 2024The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contextscited by 92
- 2023Spear Phishing With Large Language Modelscited by 49
- 2025The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating Itcited by 42
- 2024Multilingual Blending: LLM Safety Alignment Evaluation with Language Mixturecited by 22
- 2024Sandwich attack: Multi-language Mixture Adaptive Attack on LLMscited by 20
Built on by
Citing papers per year: 2026: 1.
1 paper.