Do Not Merge My Model! Safeguarding Open-Source LLMs Against Unauthorized Model Merging

Qinfeng Li, Miao Pan, Jintao Chen 0001, Fu Teng, Zhiqiang Shen, Ge Su, Hao Peng 0002, Xuhong Zhang 0002. Do Not Merge My Model! Safeguarding Open-Source LLMs Against Unauthorized Model Merging. In Sven Koenig, Chad Jenkins, Matthew E. Taylor, editors, Fortieth AAAI Conference on Artificial Intelligence, Thirty-Eighth Conference on Innovative Applications of Artificial Intelligence, Sixteenth Symposium on Educational Advances in Artificial Intelligence, AAAI 2026, Singapore, January 20-27, 2026. pages 31662-31670, AAAI Press, 2026. [doi]

Abstract

Abstract is missing.