# Evaluation of Security of ML-based Watermarking: Copy and Removal Attacks

arXiv: https://arxiv.org/abs/2409.18211 · HTML: https://mlsanity.com/paper/2409.18211/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 32 references that are in the map.
- First posted on arXiv 26 Sep 2024.

## Builds on (most cited first, 6 of 6)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [HiDDeN: Hiding Data With Deep Networks](https://mlsanity.com/paper/1807.09937/) (2018)
- [Watermarking Images in Self-Supervised Latent Spaces](https://mlsanity.com/paper/2112.09581/) (2021)
- [ROMark: A Robust Watermarking System Using Adversarial Training](https://mlsanity.com/paper/1910.01221/) (2019)

## Built on by (most cited first, 2 of 2)

- [Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Models](https://mlsanity.com/paper/2412.03283/) (2024)
- [WMCopier: Forging Invisible Image Watermarks on Arbitrary Images](https://mlsanity.com/paper/2503.22330/) (2025)

## Abstract (arXiv)

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 .