EmMark: Robust Watermarks for IP Protection of Embedded Quantized Large Language Models
Open Access
- 23 June 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Abstract
This paper introduces EmMark, a novel watermarking framework for protecting 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, ensuring robustness and maintaining model quality. Extensive proof-of-concept evaluations of models from OPT and LLaMA-2 families demonstrate EmMark's fidelity, achieving 100% success in watermark extraction with model performance preservation. EmMark also showcased its resilience against watermark removal and forging attacks.Keywords
All Related Versions
This publication has 4 references indexed in Scilit:
- Watermarking LLMs with Weight Quantization2023
- From Dense to Sparse: Contrastive Pruning for Better Pre-trained Language Model CompressionProceedings of the AAAI Conference on Artificial Intelligence, 2022
- A framework for few-shot language model evaluation2021
- SpecMark: A Spectral Watermarking Framework for IP Protection of Speech Recognition Systems2020