RoSe-Mix: Robust and Secure Deep Neural Network Watermarking in Black-Box Settings via Image Mixup
Due to their considerable costs, deep neural networks (DNNs) are valuable assets that need to be protected in terms of intellectual property (IP). From this statement, DNN watermarking gains significant interest since it allows DNN owners to prove their ownership. Various methods that embed ownershi...
Saved in:
| Main Authors: | Tamara El Hajjar, Mohammed Lansari, Reda Bellafqira, Gouenou Coatrieux, Katarzyna Kapusta, Kassem Kallas |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-03-01
|
| Series: | Machine Learning and Knowledge Extraction |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-4990/7/2/32 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
Estimation for filtering attacks on QIM watermarks
by: WANG Jin-shen, et al.
Published: (2007-01-01)
by: WANG Jin-shen, et al.
Published: (2007-01-01)
Similar Items
-
DICTION: DynamIC robusT whIte bOx Watermarking Scheme for Deep Neural Networks
by: Reda Bellafqira, et al.
Published: (2025-07-01) -
NLP neural network copyright protection based on black box watermark
by: Long DAI, et al.
Published: (2023-02-01) -
Personalized zero‐watermark algorithm based on non‐uniform weighted reconstruction and WGAN
by: Yiran Peng, et al.
Published: (2024-12-01) -
Image double fragile watermarking algorithm based on block neighborhood
by: Yilong WANG, et al.
Published: (2023-06-01) -
Chaotic Watermarking for Authentication
by: Melad Saeed
Published: (2013-07-01)