Evaluation of Security of ML-based Watermarking: Copy and Removal Attacks
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913533286940672 |
|---|---|
| author | Kinakh, Vitaliy Pulfer, Brian Belousov, Yury Fernandez, Pierre Furon, Teddy Voloshynovskiy, Slava |
| author_facet | Kinakh, Vitaliy Pulfer, Brian Belousov, Yury Fernandez, Pierre Furon, Teddy Voloshynovskiy, Slava |
| contents | 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 . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_18211 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Evaluation of Security of ML-based Watermarking: Copy and Removal Attacks Kinakh, Vitaliy Pulfer, Brian Belousov, Yury Fernandez, Pierre Furon, Teddy Voloshynovskiy, Slava Computer Vision and Pattern Recognition 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 . |
| title | Evaluation of Security of ML-based Watermarking: Copy and Removal Attacks |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.18211 |