An Information Asymmetry Game for Trigger-based DNN Model Watermarking
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915573356560384 |
|---|---|
| author | Huang, Chaoyue Zhao, Gejian Wu, Hanzhou Xia, Zhihua Malik, Asad |
| author_facet | Huang, Chaoyue Zhao, Gejian Wu, Hanzhou Xia, Zhihua Malik, Asad |
| contents | As a valuable digital product, deep neural networks (DNNs) face increasingly severe threats to the intellectual property, making it necessary to develop effective technical measures to protect them. Trigger-based watermarking methods achieve copyright protection by embedding triggers into the host DNNs. However, the attacker may remove the watermark by pruning or fine-tuning. We model this interaction as a game under conditions of information asymmetry, namely, the defender embeds a secret watermark with private knowledge, while the attacker can only access the watermarked model and seek removal. We define strategies, costs, and utilities for both players, derive the attacker's optimal pruning budget, and establish an exponential lower bound on the accuracy of watermark detection after attack. Experimental results demonstrate the feasibility of the watermarked model, and indicate that sparse watermarking can resist removal with negligible accuracy loss. This study highlights the effectiveness of game-theoretic analysis in guiding the design of robust watermarking schemes for model copyright protection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_14218 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | An Information Asymmetry Game for Trigger-based DNN Model Watermarking Huang, Chaoyue Zhao, Gejian Wu, Hanzhou Xia, Zhihua Malik, Asad Cryptography and Security As a valuable digital product, deep neural networks (DNNs) face increasingly severe threats to the intellectual property, making it necessary to develop effective technical measures to protect them. Trigger-based watermarking methods achieve copyright protection by embedding triggers into the host DNNs. However, the attacker may remove the watermark by pruning or fine-tuning. We model this interaction as a game under conditions of information asymmetry, namely, the defender embeds a secret watermark with private knowledge, while the attacker can only access the watermarked model and seek removal. We define strategies, costs, and utilities for both players, derive the attacker's optimal pruning budget, and establish an exponential lower bound on the accuracy of watermark detection after attack. Experimental results demonstrate the feasibility of the watermarked model, and indicate that sparse watermarking can resist removal with negligible accuracy loss. This study highlights the effectiveness of game-theoretic analysis in guiding the design of robust watermarking schemes for model copyright protection. |
| title | An Information Asymmetry Game for Trigger-based DNN Model Watermarking |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2510.14218 |