Preprint
Jul 2026
TextCloak: Thwarting Unauthorized LLM Exploitation via RL-Driven Unlearnable Text
Comprehensive experiments demonstrate that TextCloak consistently impairs unauthorized fine-tuning while maintaining text utility for legitimate use, highlighting its broad applicability as a practical defense against unauthorized LLM exploitation.
Chengshuai Zhao, Pingchuan Ma, Dawei Li et al.
· 0 citations