Fan Yao, Di Fuqiang, Zhang Mingqing, Wang Zichi, Liu Jia
Engineering University of PAP, Xi'an, 710086, Shaanxi, China.
School of Communication and Information Engineering Shanghai University, Shanghai, 200444, China.
Neural Netw. 2025 Jul 28;192:107918. doi: 10.1016/j.neunet.2025.107918.
Deep neural networks (DNN) have been effectively applied to perform steganographic tasks, demonstrating satisfactory performance. To ensure the secure execution of these tasks, it is essential to transmit the neural network in a secure and covert communication. A more covert communication method for transmission neural networks is to embed the neural network performing the secret task into the neural network performing the normal task. However, the existing methods for covert transmission of neural networks fail to completely transfer the neural network used for performing the secret task. This will affect the normal use of the neural network. To address this issue, this paper proposes lossless steganographic network via model arithmetic operations, which ensures that the performance and integrity of the neural network performing the secret task are not compromised ordamaged during the steganography process. We hide the parameters of the secret model using arithmetic operations between the parameters of stego model, and then train the stego model based on this to achieve the purpose of hiding the network. To ensure the stego model can effectively perform the steganography task, we employ an iterative training approach. During each training iteration, new parameters are computed and subsequently updated. Experiments show that this steganographic transmission method for secret model can securely and losslessly deliver high-performing steganographic networks to recipients.
深度神经网络（DNN）已被有效地应用于执行隐写任务，并展现出令人满意的性能。为确保这些任务的安全执行，在安全且隐蔽的通信中传输神经网络至关重要。一种更隐蔽的神经网络传输方法是将执行秘密任务的神经网络嵌入到执行正常任务的神经网络中。然而，现有的神经网络隐蔽传输方法无法完全传输用于执行秘密任务的神经网络。这将影响神经网络的正常使用。为解决此问题，本文提出了通过模型算术运算的无损隐写网络，该方法确保在隐写过程中执行秘密任务的神经网络的性能和完整性不会受到损害。我们使用隐写模型的参数之间的算术运算来隐藏秘密模型的参数，然后基于此训练隐写模型以实现隐藏网络的目的。为确保隐写模型能够有效地执行隐写任务，我们采用迭代训练方法。在每次训练迭代中，计算并随后更新新的参数。实验表明，这种针对秘密模型的隐写传输方法能够安全无损地将高性能的隐写网络传送给接收者。
