SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2501.09328 · ICML · 2026

Neural Honeytrace: Plug&Play Watermarking Framework against Model Extraction Attacks

Rui Wang, Yuan Liu, Mohan Li, Binxing Fang, Yixiao Xu, Yinghai Zhou, Zhihong Tian

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

Triggerable watermarking enables model owners to assert ownership against model extraction attacks. However, most existing approaches require additional training, which limits post-deployment flexibility, and the lack of clear theoretical foundations makes them vulnerable to adaptive attacks. In this paper, we propose Neural Honeytrace, a plug-and-play watermarking framework that operates without retraining. We redefine the watermark transmission mechanism from an information perspective, designing a training-free multistep transmission strategy that leverages the longtailed effect of backdoor learning to achieve efficient and robust watermark embedding. Extensive experiments demonstrate that Neural Honeytrace reduces the average number of queries required for a worst-case t-test-based ownership verification to as low as 2% of existing methods, while incurring zero training cost.

For agents

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

get_harvested_code_for_paper("2501.09328")
get_code_for_paper("2501.09328")
have("2501.09328")

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

curl https://syntology.ai/api/ran/2501.09328.json

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

[![Syntology run record](https://syntology.ai/api/ran/2501.09328.svg)](https://syntology.ai/paper/2501.09328)

Connect an agent — have() is free.