SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.02440 · ICML · 2025

Optimizing Adaptive Attacks against Watermarks for Language Models

Nils Lukas, Abdulrahman Diaa, Toluwani Aremu

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

Large Language Models (LLMs) can be misused to spread unwanted content at scale. Content watermarking deters misuse by hiding messages in content, enabling its detection using a secret watermarking key. Robustness is a core security property, stating that evading detection requires (significant) degradation of the content's quality. Many LLM watermarking methods have been proposed, but robustness is tested only against nonadaptive attackers who lack knowledge of the watermarking method and can find only suboptimal attacks. We formulate watermark robustness as an objective function and use preference-based optimization to tune adaptive attacks against the specific watermarking method. Our evaluation shows that (i) adaptive attacks evade detection against all surveyed watermarks, (ii) training against any watermark succeeds in evading unseen watermarks, and (iii) optimization-based attacks are cost-effective. Our findings underscore the need to test robustness against adaptively tuned attacks. We release our adaptively tuned paraphrasers at https://github.com/nilslukas/ada -wm-evasion.

For agents

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

get_harvested_code_for_paper("2410.02440")
get_code_for_paper("2410.02440")
have("2410.02440")

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

curl https://syntology.ai/api/ran/2410.02440.json

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

[![Syntology run record](https://syntology.ai/api/ran/2410.02440.svg)](https://syntology.ai/paper/2410.02440)

Connect an agent — have() is free.