{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/char-mander-use-mbackdoor-a-study-of-cross","title":"Char-mander Use mBackdoor! A Study of Cross-lingual Backdoor Attacks in Multilingual LLMs","arxiv_id":"2502.16901","date":"2025-02-24","proceeding":null,"authors":["Himanshu Beniwal","Sailesh Panda","Birudugadda Srivibhav","Mayank Singh"],"abstract":"We explore \\textbf{C}ross-lingual \\textbf{B}ackdoor \\textbf{AT}tacks (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 expose a critical vulnerability that influences the model's architecture, resulting in a concealed backdoor effect during the information flow. Our code and data are publicly available https://github.com/himanshubeniwal/X-BAT.","url_abs":"https://arxiv.org/abs/2502.16901v2","url_pdf":"https://arxiv.org/pdf/2502.16901v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"char-mander-use-mbackdoor-a-study-of-cross","repo_url":"https://github.com/himanshubeniwal/x-bat","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"cross-lingual-transfer","task_name":"Cross-Lingual Transfer"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}