Char-mander Use mBackdoor! A Study of Cross-lingual Backdoor Attacks in Multilingual LLMs

AbstractWe explore Cross-lingual Backdoor ATtacks (X-BAT) in multilingual Large Language Models (mLLMs), revealing how backdoors inserted in one language can automatically transfer to others through shared embedding spaces. Using toxicity classification as a case study, we demonstrate that attackers can compromise multilingual systems by poisoning data in a single language, with rare and high-occurring tokens serving as specific, effective triggers. Our findings reveal a critical vulnerability that affects the model’s architecture, leading to a concealed backdoor effect during the information flow. Our code and data are publicly available at https://github.com/himanshubeniwal/X-BAT.