mlsanityData to 7 Oct 2026

A Cross-Language Investigation into Jailbreak Attacks in Large Language Models

arXiv 2401.16765 ↗First posted 30 Jan 2024cs.CR cs.AIcited by 37

On the map: LLM safety and security → Jailbreaking

Abstract (arXiv)

Large Language Models (LLMs) have become increasingly popular for their advanced text generation capabilities across various domains. However, like any software, they face security challenges, including the risk of 'jailbreak' attacks that manipulate LLMs to produce prohibited content. A particularly underexplored area is the Multilingual Jailbreak attack, where malicious questions are translated into various languages to evade safety filters. Currently, there is a lack of comprehensive empirical studies addressing this specific threat. To address this research gap, we conducted an extensive empirical study on Multilingual Jailbreak attacks. We developed a novel semantic-preserving algorithm to create a multilingual jailbreak dataset and conducted an exhaustive evaluation on both widely-used open-source and commercial LLMs, including GPT-4 and LLaMa. Additionally, we performed interpretability analysis to uncover patterns in Multilingual Jailbreak attacks and implemented a fine-tuning mitigation method. Our findings reveal that our mitigation strategy significantly enhances model defense, reducing the attack success rate by 96.2%. This study provides valuable insights into understanding and mitigating Multilingual Jailbreak attacks.

Key facts. Cited by 37 papers in the map (data through 7 Oct 2026). Placed in Jailbreaking, one of 12 directions in LLM safety and security. Builds on 22 of its 39 references that are in the map. First posted on arXiv 30 Jan 2024.

Builds on

22 of 39 references.

Closest ancestors · 5

Same direction, newest first

  1. 2023DeepInception: Hypnotize Large Language Model to Be Jailbreaker6 Nov
  2. 2023Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks16 Oct
  3. 2023Low-Resource Languages Jailbreak GPT-43 Oct
  4. 2023PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts7 Jun
  5. 2023Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study23 May

Other references · 17

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  5. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,543
  6. 2016Understanding intermediate layers using linear classifier probescited by 1,279
  7. 2014Striving for Simplicity: The All Convolutional Netcited by 983
  8. 2022Red Teaming Language Models with Language Modelscited by 983
  9. 2018A Survey Of Methods For Explaining Black Box Modelscited by 970
  10. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitycited by 888
  11. 2020Transformer Interpretability Beyond Attention Visualizationcited by 620
  12. 2022Improving alignment of dialogue agents via targeted human judgementscited by 527
5 more
  1. 2019Interpretable machine learning: definitions, methods, and applicationscited by 303
  2. 2019A Multiscale Visualization of Attention in the Transformer Modelcited by 292
  3. 2020A Survey on Neural Network Interpretabilitycited by 291
  4. 2023ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learningcited by 203
  5. 2021A Survey on Understanding, Visualizations, and Explanation of Deep Neural Networkscited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 13; 2025: 17; 2026: 7.

37 papers.

Sort:

By area:

  1. 2024Jailbreak Attacks and Defenses Against Large Language Models: A Surveycited by 215
  2. 2024The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harmcited by 67
  3. 2024Fight Back Against Jailbreaking via Prompt Adversarial Tuningcited by 63
  4. 2025Safety at Scale: A Comprehensive Survey of Large Model and Agent Safetycited by 63
  5. 2024SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Mannercited by 57
  6. 2025Refusal Direction is Universal Across Safety-Aligned Languagescited by 37
  7. 2024Jailbreaking and Mitigation of Vulnerabilities in Large Language Modelscited by 33
  8. 2024JailbreakEval: An Integrated Toolkit for Evaluating Jailbreak Attempts Against Large Language Modelscited by 28
  9. 2025Multilingual and Multi-Accent Jailbreaking of Audio LLMscited by 25
  10. 2025EmoAgent: Assessing and Safeguarding Human-AI Interaction for Mental Health Safetycited by 21
  11. 2024The Dark Side of Function Calling: Pathways to Jailbreaking Large Language Modelscited by 20
  12. 2024Multilingual Large Language Models: A Systematic Surveycited by 18
25 more
  1. 2025SoK: Evaluating Jailbreak Guardrails for Large Language Modelscited by 17
  2. 2025Attack and defense techniques in large language models: A survey and new perspectivescited by 13
  3. 2024LLMs Can Defend Themselves Against Jailbreaking in a Practical Manner: A Vision Papercited by 9
  4. 2024Evaluating and Mitigating Linguistic Discrimination in Large Language Modelscited by 8
  5. 2024Can LLMs be Fooled? Investigating Vulnerabilities in LLMscited by 5
  6. 2025SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defensescited by 4
  7. 2024Towards Safe Multilingual Frontier AIcited by 2
  8. 2025Jailbreaking Large Language Models in Infinitely Many Wayscited by 2
  9. 2025ArtPerception: ASCII Art-based Jailbreak on LLMs with Recognition Pre-testcited by 2
  10. 2025Tailored untruths: How personalisation challenges LLM safeguardscited by 2
  11. 2024Divide and Conquer: A Hybrid Strategy Defeats Multimodal Large Language Modelscited by 1
  12. 2025Strategic Deflection: Defending LLMs from Logit Manipulationcited by 1
  13. 2025Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generationcited by 1
  14. 2025NeuroBreak: Unveil Internal Jailbreak Mechanisms in Large Language Modelscited by 1
  15. 2025LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systemscited by 1
  16. 2026A Systematic Review of Algorithmic Red Teaming Methodologies for Assurance and Security of AI Applicationscited by 1
  17. 2026Multilingual Safety Alignment via Self-Distillationcited by 1
  18. 2026Multilingual jailbreaking of LLMs using low-resource languagescited by 1
  19. 2025TestDG: Test-time Domain Generalization for Continual Test-time Adaptationcited by 0
  20. 2025Improving LLM Outputs Against Jailbreak Attacks with Expert Model Integrationcited by 0
  21. 2025Sentra-Guard: A Real-Time Multilingual Defense Against Adversarial LLM Promptscited by 0
  22. 2026A Causal Perspective for Enhancing Jailbreak Attack and Defensecited by 0
  23. 2026Cross-Lingual Jailbreak Detection via Semantic Codebookscited by 0
  24. 2026AlcaTRAz - Anchored Tree-Rule Defense Against Jailbreakscited by 0
  25. 2026Arbitrary Cipher Attacks Against Large Language Models Do Not Require Fine-Tuningcited by 0