Beniwal, HimanshuPanda, SaileshSingh, Mayank2025-08-282025-08-282025-02-01http://arxiv.org/abs/2502.16901https://d8.irins.org/handle/IITG2025/19908We 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 tokens serving as specific effective triggers. Our findings expose a critical vulnerability in the fundamental architecture that enables cross-lingual transfer in these models. Our code and data are publicly available at this https URL.en-USe-Printe-Print123456789/435