EmMark: Robust Watermarks for IP Protection of Embedded Quantized Large Language Models
CoRR(2024)
摘要
This paper introduces EmMark,a novel watermarking framework for protecting
the intellectual property (IP) of embedded large language models deployed on
resource-constrained edge devices. To address the IP theft risks posed by
malicious end-users, EmMark enables proprietors to authenticate ownership by
querying the watermarked model weights and matching the inserted signatures.
EmMark's novelty lies in its strategic watermark weight parameters selection,
nsuring robustness and maintaining model quality. Extensive proof-of-concept
evaluations of models from OPT and LLaMA-2 families demonstrate EmMark's
fidelity, achieving 100
preservation. EmMark also showcased its resilience against watermark removal
and forging attacks.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要