Evaluation of Security of ML-based Watermarking: Copy and Removal Attacks
Abstract
The vast amounts of digital content captured from the real world or AI-generated media necessitate methods for copyright protection, traceability, or data provenance verification. Digital watermarking serves as a crucial approach to address these challenges. Its evolution spans three generations: handcrafted, autoencoder-based, and foundation model based methods. While the robustness of these systems is well-documented, the security against adversarial attacks remains underexplored. This paper evaluates the security of foundation models' latent space digital watermarking systems that utilize adversarial embedding techniques. A series of experiments investigate the security dimensions under copy and removal attacks, providing empirical insights into these systems' vulnerabilities. All experimental codes and results are available at https://github.com/vkinakh/ssl-watermarking-attacks .
Keywords
Cite
@article{arxiv.2409.18211,
title = {Evaluation of Security of ML-based Watermarking: Copy and Removal Attacks},
author = {Vitaliy Kinakh and Brian Pulfer and Yury Belousov and Pierre Fernandez and Teddy Furon and Slava Voloshynovskiy},
journal= {arXiv preprint arXiv:2409.18211},
year = {2024}
}