Skip to main navigation Skip to search Skip to main content

MW-MAS: A Multi-agent System for Multimodal Watermarking with Agent Orchestration

  • Sungkyunkwan University
  • Korea Information and Security Agency

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Recent advances in generative models enabled the creation of high-quality synthetic text and images, raising concerns about provenance and misuse. We propose MW-MAS (Multimodal Watermarking Multi-Agent System), a unified framework that orchestrates watermarking across text and image modalities via three agents: the Text Watermark Agent, Image Watermark Agent, and Orchestration Agent. The Orchestration Agent adaptively selects optimal agent combinations based on sample characteristics. Evaluated on the WIT dataset, MW-MAS achieves up to 2× faster runtime than dual-agent baselines while maintaining high fidelity and robust bit-level watermark retrieval, offering a flexible and practical solution for multimodal content watermarking. Code is available at https://github.com/lynnchoi0126/MW-MAS.

Original languageEnglish
Title of host publicationPRIMA 2025
Subtitle of host publicationPrinciples and Practice of Multi-Agent Systems - 26th International Conference, Proceedings
EditorsCatalin Dima, Angelo Ferrando, Vadim Malvone
PublisherSpringer Science and Business Media Deutschland GmbH
Pages339-347
Number of pages9
ISBN (Print)9783032135612
DOIs
StatePublished - 2026
Event26th International Conference on Principles and Practice of Multi-Agent Systems, PRIMA 2025 - Modena, Italy
Duration: 16 Dec 202519 Dec 2025

Publication series

NameLecture Notes in Computer Science
Volume16366 LNAI
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference26th International Conference on Principles and Practice of Multi-Agent Systems, PRIMA 2025
Country/TerritoryItaly
CityModena
Period16/12/2519/12/25

Keywords

  • Agent Orchestration
  • Multi-Agent Systems
  • Multi-modal Watermark

Fingerprint

Dive into the research topics of 'MW-MAS: A Multi-agent System for Multimodal Watermarking with Agent Orchestration'. Together they form a unique fingerprint.

Cite this