Lune

EMNLP Findings2025

Multilingual Collaborative Defense for Large Language Models

Hongliang Li, Jinan Xu, Gengping Cui, Changhao Guan, Fengran Mo, Kaiyu Huang

Abstract

The robustness and security of Large Language Models (LLMs) face increasing threats, especially in multilingual settings. A notable vulnerability is "jailbreaking" via translating harmful queries into rare or underrepresented languages, which often bypasses existing safeguards. In this work, we propose Multilingual Collaborative Defense (MCD), a novel learning method that optimizes a continuous soft safety prompt automatically to facilitate multilingual safeguarding of LLMs. MCD organically leverages collaborative signals from multiple languages by rotating each as the training "center," allowing auxiliary languages to reinforce safety prompt learning and ensuring cross-lingual consistency. As a result, MCD improves defense performance across all languages, reduces false refusals, and mitigates safety misalignment caused by corpus imbalance. To evaluate MCD, we construct multilingual versions of jailbreak benchmarks such as MaliciousInstruct and AdvBench, including zero-shot languages, to assess language transferability. Experiments show that MCD outperforms prior approaches in multilingual jailbreak defense while exhibiting strong crosslingual generalization. Our code is available at https://github.com/HLiang-Lee/MCD.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability cites Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation
  • Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks cites Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on13

  1. Catastrophic Jailbreak of Open-source LLMs via Exploiting GenerationYangsibo Huang, Samyak Gupta, Mengzhou Xia, Kai Li et al.ICLR 2024 · 481 citations
  2. Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow InstructionsFederico Bianchi, Mirac Suzgun, Giuseppe Attanasio, Paul Röttger et al.ICLR 2024 · 373 citations
  3. Multilingual Jailbreak Challenges in Large Language ModelsYue Deng, Wenxuan Zhang, Sinno Jialin Pan, Lidong BingICLR 2024 · 230 citations
  4. Robust Prompt Optimization for Defending Language Models Against Jailbreaking AttacksAndy Zhou, Bo Li, Haohan WangNeurIPS 2024 · 198 citations
  5. COLD-Attack: Jailbreaking LLMs with Stealthiness and ControllabilityXingang Guo, Fangxu Yu, Huan Zhang, Lianhui Qin et al.ICML 2024 · 173 citations

Related papers

  1. English as Defense Proxy: Mitigating Multilingual Jailbreak via Eliciting English Safety KnowledgeZekai Zhang, Yiduo Guo, Jiuheng Lin, Shanghaoran Quan et al.EMNLP Findings 2025
  2. MrGuard: A Multilingual Reasoning Guardrail for Universal LLM SafetyYahan Yang, Soham Dan, Shuo Li, Dan Roth et al.EMNLP 2025
  3. Defending LLMs against Jailbreaking Attacks via BacktranslationYihan Wang, Zhouxing Shi, Andrew Bai, Cho-Jui HsiehACL Findings 2024 · 28 citations
  4. How Jailbreak Defenses Work and Ensemble? A Mechanistic InvestigationZhuohan Long, Siyuan Wang, Shujun Liu, Yuhang LaiEMNLP Findings 2025 · 1 citation
  5. AdvPrompter: Fast Adaptive Adversarial Prompting for LLMsAnselm Paulus, Arman Zharmagambetov, Chuan Guo, Brandon Amos et al.ICML 2025
Dusk over the sea between two cliffs drawn in fine vertical lines