SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2309.04777 · ICCV · 2023

Towards Robust Model Watermark via Reducing Parametric Vulnerability

Dongxian Wu, Shu-Tao Xia, Yiming Li, Guanhao Gan

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

Deep neural networks are valuable assets considering their commercial benefits and huge demands for costly annotation and computation resources. To protect the copyright of DNNs, backdoor-based ownership verification becomes popular recently, in which the model owner can watermark the model by embedding a specific backdoor behavior before releasing it. The defenders (usually the model owners) can identify whether a suspicious thirdparty model is "stolen" from them based on the presence of the behavior. Unfortunately, these watermarks are proven to be vulnerable to removal attacks even like finetuning. To further explore this vulnerability, we investigate the parameter space and find there exist many watermarkremoved models in the vicinity of the watermarked one, which may be easily used by removal attacks. Inspired by this finding, we propose a mini-max formulation to find these watermark-removed models and recover their watermark behavior. Extensive experiments demonstrate that our method improves the robustness of the model watermarking against parametric changes and numerous watermarkremoval attacks. The codes for reproducing our main experiments are available at https://github.com/ GuanhaoGan/robust-model-watermarking.

For agents

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

get_harvested_code_for_paper("2309.04777")
get_code_for_paper("2309.04777")
have("2309.04777")

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

curl https://syntology.ai/api/ran/2309.04777.json

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

[![Syntology run record](https://syntology.ai/api/ran/2309.04777.svg)](https://syntology.ai/paper/2309.04777)

Connect an agent — have() is free.