mlsanityData to 7 Oct 2026

JailNewsBench: Multi-Lingual and Regional Benchmark for Fake News Generation under Jailbreak Attacks

arXiv 2603.01291 ↗First posted 1 Mar 2026cs.LG cs.CLcited by 6

On the map: LLM safety and security → Jailbreaking

Abstract (arXiv)

Fake news undermines societal trust and decision-making across politics, economics, health, and international relations, and in extreme cases threatens human lives and societal safety. Because fake news reflects region-specific political, social, and cultural contexts and is expressed in language, evaluating the risks of large language models (LLMs) requires a multi-lingual and regional perspective. Malicious users can bypass safeguards through jailbreak attacks, inducing LLMs to generate fake news. However, no benchmark currently exists to systematically assess attack resilience across languages and regions. Here, we propose JailNewsBench, the first benchmark for evaluating LLM robustness against jailbreak-induced fake news generation. JailNewsBench spans 34 regions and 22 languages, covering 8 evaluation sub-metrics through LLM-as-a-Judge and 5 jailbreak attacks, with approximately 300k instances. Our evaluation of 9 LLMs reveals that the maximum attack success rate (ASR) reached 86.3% and the maximum harmfulness score was 3.5 out of 5. Notably, for English and U.S.-related topics, the defensive performance of typical multi-lingual LLMs was significantly lower than for other regions, highlighting substantial imbalances in safety across languages and regions. In addition, our analysis shows that coverage of fake news in existing safety datasets is limited and less well defended than major categories such as toxicity and social bias. Our dataset and code are available at https://github.com/kanekomasahiro/jail_news_bench.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Placed in Jailbreaking, one of 12 directions in LLM safety and security. Builds on 65 of its 83 references that are in the map. First posted on arXiv 1 Mar 2026.

Builds on

65 of 83 references.

Closest ancestors · 15

Same direction, newest first

  1. 2025Online Learning Defense against Iterative Jailbreak Attacks via Prompt Optimization19 Oct
  2. 2025The Jailbreak Tax: How Useful are Your Jailbreak Outputs?14 Apr
  3. 2025SafeDialBench: A Fine-Grained Safety Evaluation Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak Attacks16 Feb
  4. 2025Defense Against the Dark Prompts: Mitigating Best-of-N Jailbreaking with Prompt Evaluation1 Feb
  5. 2024Cognitive Overload Attack:Prompt Injection for Long Context15 Oct
  6. 2024JAILJUDGE: A Comprehensive Jailbreak Judge Benchmark with Multi-Agent Enhanced Explanation Evaluation Framework11 Oct
  7. 2024RoleBreak: Character Hallucination as a Jailbreak Attack in Role-Playing Systems25 Sep
  8. 2024Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs13 Jun
  9. 2024SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner8 Jun
  10. 2024JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models28 Mar
  11. 2024Don't Listen To Me: Understanding and Exploring Jailbreak Prompts of Large Language Models26 Mar
  12. 2023Multilingual Jailbreak Challenges in Large Language Models10 Oct
3 more
  1. 2023Universal and Transferable Adversarial Attacks on Aligned Language Models27 Jul
  2. 2023Jailbroken: How Does LLM Safety Training Fail?5 Jul
  3. 2023Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study23 May

Other references · 50

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  3. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  4. 2017Deep reinforcement learning from human preferencescited by 3,846
  5. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  6. 2023Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!cited by 1,106
  7. 2023BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Datasetcited by 828
  8. 2022Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learnedcited by 702
  9. 2023The Internal State of an LLM Knows When It's Lyingcited by 644
  10. 2019Defending Against Neural Fake Newscited by 553
  11. 2017"Liar, Liar Pants on Fire": A New Benchmark Dataset for Fake News Detectioncited by 361
  12. 2024INSIDE: LLMs' Internal States Retain the Power of Hallucination Detectioncited by 317
38 more
  1. 2018FakeNewsNet: A Data Repository with News Content, Social Context and Spatialtemporal Information for Studying Fake News on Social Mediacited by 281
  2. 2023SafetyBench: Evaluating the Safety of Large Language Modelscited by 189
  3. 2023Can LLM-Generated Misinformation Be Detected?cited by 173
  4. 2017Automatic Detection of Fake Newscited by 145
  5. 2023The science of fake newscited by 94
  6. 2024Unsupervised Real-Time Hallucination Detection based on the Internal States of Large Language Modelscited by 84
  7. 2023AI model GPT-3 (dis)informs us better than humanscited by 75
  8. 2023Bad Actor, Good Advisor: Exploring the Role of Large Language Models in Fake News Detectioncited by 69
  9. 2023Fake News in Sheep's Clothing: Robust Fake News Detection Against LLM-Empowered Style Attackscited by 69
  10. 2020FakeCovid -- A Multilingual Cross-domain Fact Check News Dataset for COVID-19cited by 60
  11. 2024Evaluating Gender Bias in Large Language Models via Chain-of-Thought Promptingcited by 49
  12. 2024On Large Language Models' Hallucination with Regard to Known Factscited by 43
  13. 2020Fighting the COVID-19 Infodemic in Social Media: A Holistic Perspective and a Call to Armscited by 41
  14. 2020BanFakeNews: A Dataset for Detecting Fake News in Banglacited by 40
  15. 2020MM-COVID: A Multilingual and Multimodal Data Repository for Combating COVID-19 Disinformationcited by 36
  16. 2024Exploring the Deceptive Power of LLM-Generated Fake News: A Study of Real-World Detection Challengescited by 28
  17. 2023Disentangling Perceptions of Offensiveness: Cultural and Moral Correlatescited by 26
  18. 2025LLM-Generated Fake News Induces Truth Decay in News Ecosystem: A Case Study on Neural News Recommendationcited by 19
  19. 2023FakeGPT: Fake News Generation, Explanation and Detection of Large Language Modelscited by 16
  20. 2023Adapting Fake News Detection to the Era of Large Language Modelscited by 14
  21. 2020No Rumours Please! A Multi-Indic-Lingual Approach for COVID Fake-Tweet Detectioncited by 13
  22. 2025LinguaSafe: A Comprehensive Multilingual Safety Benchmark for Large Language Modelscited by 13
  23. 2019Reducing malicious use of synthetic media research: Considerations and potential release practices for machine learningcited by 12
  24. 2023Prompt-and-Align: Prompt-Based Social Alignment for Few-Shot Fake News Detectioncited by 11
  25. 2024Likelihood-based Mitigation of Evaluation Bias in Large Language Modelscited by 9
  26. 2020Advanced Machine Learning Techniques for Fake News (Online Disinformation) Detection: A Systematic Mapping Studycited by 8
  27. 2021Profiling Fake News Spreaders on Social Media through Psychological and Motivational Factorscited by 7
  28. 2024A Little Leak Will Sink a Great Ship: Survey of Transparency for Large Language Models from Start to Finishcited by 6
  29. 2024A diverse Multilingual News Headlines Dataset from around the Worldcited by 6
  30. 2026Paraphrasing Adversarial Attack on LLM-as-a-Reviewercited by 6
  31. 2024Emotional Manipulation Through Prompt Engineering Amplifies Disinformation Generation in AI Large Language Modelscited by 5
  32. 2024Learn to Disguise: Avoid Refusal Responses in LLM's Defense via a Multi-agent Attacker-Disguiser Gamecited by 5
  33. 2025Intent-Aware Self-Correction for Mitigating Social Biases in Large Language Modelscited by 5
  34. 2025VaxGuard: A Multi-Generator, Multi-Type, and Multi-Role Dataset for Detecting LLM-Generated Vaccine Misinformationcited by 5
  35. 2024LLM-GAN: Construct Generative Adversarial Network Through Large Language Models For Explainable Fake News Detectioncited by 4
  36. 2025Online Safety for All: Sociocultural Insights from a Systematic Review of Youth Online Safety in the Global Southcited by 3
  37. 2023FakeWatch ElectionShield: A Benchmarking Framework to Detect Fake News for Credible US Electionscited by 2
  38. 2024Multi-modal, Multi-task, Multi-criteria Automatic Evaluation with Vision Language Modelscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026XL-SafetyBench: A Country-Grounded Cross-Cultural Benchmark for LLM Safety and Cultural Sensitivitycited by 1
  2. 2026Large Language Models in Misinformation Ecosystems: Misuse, Defense, and Vulnerabilitycited by 0
  3. 2026In-Context Learning as Implicit Policy Gradientcited by 0
  4. 2026IndicSafeEval: Safety Robustness of Large Language Models under Multilingual Persuasive Jailbreak Attackscited by 0
  5. 2026FakeSpotter: A content and strategy agnostic Viral Misinformation Detection Toolcited by 0
  6. 2026VEX-Bench: Benchmarking Verification Complexity of LLM-Generated Misinformationcited by 0