Lune

EMNLP Findings2025

English as Defense Proxy: Mitigating Multilingual Jailbreak via Eliciting English Safety Knowledge

Zekai Zhang, Yiduo Guo, Jiuheng Lin, Shanghaoran Quan, Huishuai Zhang, Dongyan Zhao

Abstract

Large language models (LLMs) excel in many tasks, but their safety guarantees vary by languages, e.g., responses in English tend to be safer than those in low-resource languages. This inconsistency creates a vulnerability, since an attacker can circumvent safety measures by using a less-supported language as an intermediary, even without fluency in that language. Traditional solutions rely on multilingual safety alignment, which demands vast, per-language datasets and introduces significant trade-offs between usefulness and safety (the so-called "alignment tax"). To overcome these limitations, we introduce English as Defense Proxy (E-Proxy), a unified approach that leverages English, usually the advantage language of LLMs, as a universal safety anchor. During multilingual training, E-Proxy uses English jailbreak prompts to extract the model's existing safety knowledge, then applies simple language-mapping prompts (e.g., "Please answer in target language") to transfer that knowledge across languages. Our analysis shows that formulating prompts in a highresource language preserves the model's utility, while enforcing responses in the target language significantly enhances safety. We evaluate E-Proxy on extensive benchmarks of both attack resistance and task performance. On the MultiJail benchmark, E-Proxy blocks over 99 % of jailbreak attempts while retaining 95 % of average task performance, all with a carefully constructed multilingual alignment data.

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

Builds onCited byLeft to right by year; the more cited, the higher.

Builds on17

  1. LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
  2. Measuring Massive Multitask Language UnderstandingDan Hendrycks, Collin Burns, Steven Basart, Andy Zou et al.ICLR 2021 · 7,905 citations
  3. Prompting Large Language Model for Machine Translation: A Case StudyBiao Zhang, Barry Haddow, Alexandra BirchICML 2023 · 402 citations
  4. Multilingual Jailbreak Challenges in Large Language ModelsYue Deng, Wenxuan Zhang, Sinno Jialin Pan, Lidong BingICLR 2024 · 230 citations
  5. RAIN: Your Language Models Can Align Themselves without FinetuningYuhui Li, Fangyun Wei, Jinjing Zhao, Chao Zhang et al.ICLR 2024 · 171 citations

Related papers

  1. Multilingual Collaborative Defense for Large Language ModelsHongliang Li, Jinan Xu, Gengping Cui, Changhao Guan et al.EMNLP Findings 2025 · 2 citations
  2. Logic Jailbreak: Efficiently Unlocking LLM Safety Restrictions Through Formal Logical ExpressionJingyu Peng, Maolin Wang, Nan Wang, Jiatong Li et al.ACL Findings 2026 · 4 citations
  3. Experience-Driven Multi-Agent Optimization for Black-Box Jailbreak Attacks on Large Language ModelsZhaoyang Han, Yihe Liu, Kai Zhang, Ping LiACL Findings 2026
  4. MrGuard: A Multilingual Reasoning Guardrail for Universal LLM SafetyYahan Yang, Soham Dan, Shuo Li, Dan Roth et al.EMNLP 2025
  5. Defending LLMs against Jailbreaking Attacks via BacktranslationYihan Wang, Zhouxing Shi, Andrew Bai, Cho-Jui HsiehACL Findings 2024 · 28 citations
Dusk over the sea between two cliffs drawn in fine vertical lines