Meta Security Metric Learning for Secure Deep Image Hiding
- 8 February 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 21 (5) , 4907-4920
Abstract
Deep Image Hiding (DIH) aims to imperceptibly hide images within image. To improve its security performance, some DIH methods design Security Metrics (SMs) to guide the learning of their hiding networks. However, these methods focus on optimizing their anti-steganalysis ability on specific SMs, resulting in inferior generalization ability. To overcome these limitations, in this paper, we introduce meta-learning into DIH and propose Meta Security Metric-based DIH (MSM-DIH). In the MSM-DIH, the Invertible Neural Network (INN)-based hiding network is learned under the guidance of a learnable meta SM generalized from multiple fixed source SMs, and each SM is composed of a metric network and a contrastive loss function. Specifically, MSM-DIH is trained with bi-level optimization. In the outer optimization, a meta SM is learned to assign higher security scores for more advanced stego images. Besides, the domain knowledge of steganalysis is transferred from the multiple pre-trained source metric networks to the meta metric network, so as to enhance the generalization ability of the meta SM. In the inner optimization, the hiding network is learned to generate more secure stego images according to the learned meta SM. Experimental results show that our MSM-DIH has achieved the best security performance in most cases.Keywords
Funding Information
- National Natural Science Foundation of China (62372125, 62002075, 61972205, U1936218)
- Guangdong Natural Science Funds for Distinguished Young Scholar (2023B1515020041)
- Basic and Applied Basic Research Foundation of Guangdong Province (2023A1515011428)
This publication has 69 references indexed in Scilit:
- HCISNet: Higher‐capacity invisible image steganographic networkIET Image Processing, 2021
- A data hiding scheme based on U-Net and wavelet transformKnowledge-Based Systems, 2021
- Large-capacity Image Steganography Based on Invertible Neural Networks2021
- Invertible Image Signal Processing2021
- StegaStamp: Invisible Hyperlinks in Physical Photographs2020
- ManTra-Net: Manipulation Tracing Network for Detection and Localization of Image Forgeries With Anomalous Features2019
- Invisible steganography via generative adversarial networksMultimedia Tools and Applications, 2018
- HiDDeN: Hiding Data With Deep Networks2018
- Deep Adversarial Metric Learning2018
- Perturbed quantization steganographyMultimedia Systems, 2005