SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.03162 · ICML · 2023

Protecting Language Generation Models via Invisible Watermarking

Yu-Xiang Wang, Lei Li, Xuandong Zhao

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Language generation models have been an increasingly powerful enabler for many applications. Many such models offer free or affordable API access, which makes them potentially vulnerable to model extraction attacks through distillation. To protect intellectual property (IP) and ensure fair use of these models, various techniques such as lexical watermarking and synonym replacement have been proposed. However, these methods can be nullified by obvious countermeasures such as "synonym randomization". To address this issue, we propose GINSEW, a novel method to protect text generation models from being stolen through distillation. The key idea of our method is to inject secret signals into the probability vector of the decoding steps for each target token. We can then detect the secret message by probing a suspect model to tell if it is distilled from the protected one. Experimental results show that GINSEW can effectively identify instances of IP infringement with minimal impact on the generation quality of protected APIs. Our method demonstrates an absolute improvement of 19 to 29 points on mean average precision (mAP) in detecting suspects compared to previous methods against watermark removal attacks.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2302.03162")
get_code_for_paper("2302.03162")
have("2302.03162")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2302.03162.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2302.03162.svg)](https://syntology.ai/paper/2302.03162)

Connect an agent — have() is free.