A CRDNet‐Based Watermarking Algorithm for Fused Visible–Infrared Images

Infrared images often involve trade secrets. In order to protect the information security of infrared images, using a robust watermarking algorithm based on infrared images is a fitting solution. Recently, many effective visible and infrared image fusion (VIF) algorithms have been proposed in medicine, biology, and geology. Robust watermarking algorithms can resist mild conventional attacks, and with the progress of science and technology, algorithmic robustness against novel attacks such as screen shooting and print shooting has also become a research hotspot. However, VIF‐based image watermarking algorithms are still scarce. It is important to investigate a robust watermarking algorithm that can resist VIF attacks. Herein, an autoencoder against infrared fusion attacks is proposed based on various subnetworks: CRDnet (Convolutional Residual Dense Network). CRDnet includes encoders and decoders based on residual and dense structures, a fusion network robust to 12 VIF algorithms, and predictors for predicting watermarked infrared images. The encoder and decoder also incorporate preprocessing steps, attention mechanisms, and activation functions suitable for infrared images. The experimental results demonstrate that the bit error rate of CRDnet is reduced by at least ≈4% compared to common autoencoders. The peak signal‐to‐noise ratio of watermarked images is also almost always greater than 38 dB.