Revisiting the Information Capacity of Neural Network Watermarks: Upper Bound Estimation and Beyond
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914685994926080 |
|---|---|
| author | Li, Fangqi Zhao, Haodong Du, Wei Wang, Shilin |
| author_facet | Li, Fangqi Zhao, Haodong Du, Wei Wang, Shilin |
| contents | To trace the copyright of deep neural networks, an owner can embed its identity information into its model as a watermark. The capacity of the watermark quantify the maximal volume of information that can be verified from the watermarked model. Current studies on capacity focus on the ownership verification accuracy under ordinary removal attacks and fail to capture the relationship between robustness and fidelity. This paper studies the capacity of deep neural network watermarks from an information theoretical perspective. We propose a new definition of deep neural network watermark capacity analogous to channel capacity, analyze its properties, and design an algorithm that yields a tight estimation of its upper bound under adversarial overwriting. We also propose a universal non-invasive method to secure the transmission of the identity message beyond capacity by multiple rounds of ownership verification. Our observations provide evidence for neural network owners and defenders that are curious about the tradeoff between the integrity of their ownership and the performance degradation of their products. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_12720 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Revisiting the Information Capacity of Neural Network Watermarks: Upper Bound Estimation and Beyond Li, Fangqi Zhao, Haodong Du, Wei Wang, Shilin Cryptography and Security Artificial Intelligence To trace the copyright of deep neural networks, an owner can embed its identity information into its model as a watermark. The capacity of the watermark quantify the maximal volume of information that can be verified from the watermarked model. Current studies on capacity focus on the ownership verification accuracy under ordinary removal attacks and fail to capture the relationship between robustness and fidelity. This paper studies the capacity of deep neural network watermarks from an information theoretical perspective. We propose a new definition of deep neural network watermark capacity analogous to channel capacity, analyze its properties, and design an algorithm that yields a tight estimation of its upper bound under adversarial overwriting. We also propose a universal non-invasive method to secure the transmission of the identity message beyond capacity by multiple rounds of ownership verification. Our observations provide evidence for neural network owners and defenders that are curious about the tradeoff between the integrity of their ownership and the performance degradation of their products. |
| title | Revisiting the Information Capacity of Neural Network Watermarks: Upper Bound Estimation and Beyond |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2402.12720 |