Most of today’s secret image sharing (SIS) schemes are based on Shamir’s polynomial-based secret sharing (SS), which cannot recover pixels larger than 250. Many exiting methods of lossless recovery are not perfect, because several problems arise, such as large computational costs, pixel expansion and uneven pixel distribution of shadow image. In order to solve these problems and achieve perfect lossless recovery and efficiency, we propose a scheme based on matrix theory modulo 256, which satisfies $(k,k)$ and $(k,k+1)$ thresholds. Firstly, a sharing matrix is generated by the filter operation, which is used to encrypt the secret image into n shadow images, and then the secret image can be obtained by matrix inverse and matrix multiplication with k or more shadows in the recovery phase. Both theoretical analyses and experiments are conducted to demonstrate the effectiveness of the proposed scheme.

Generative linguistic steganography encodes candidate words with conditional probability when generating text by language model, and then, it selects the corresponding candidate words to output according to the confidential message to be embedded, thereby generating steganographic text. The encoding techniques currently used in generative text steganography fall into two categories: fixed-length coding and variable-length coding. Because of the simplicity of coding and decoding and the small computational overhead, fixed-length coding is more suitable for resource-constrained environments. However, the conventional text steganography mode selects and outputs a word at one time step, which is highly susceptible to the influence of confidential information and thus may select words that do not match the statistical distribution of the training text, reducing the quality and concealment of the generated text. In this paper, we inherit the decoding advantages of fixed-length coding, focus on solving the problems of existing steganography methods, and propose a multi-time-step-based steganography method, which integrates multiple time steps to select words that can carry secret information and fit the statistical distribution, thus effectively improving the text quality. In the experimental part, we choose the GPT-2 language model to generate the text, and both theoretical analysis and experiments prove the effectiveness of the proposed scheme.

In recent years, the wide application of deep neural network models has brought serious risks of intellectual property rights infringement. Embedding a watermark in a network model is an effective solution to protect intellectual property rights. Although researchers have proposed schemes to add watermarks to models, they cannot prevent attackers from adding and overwriting original information, and embedding rates cannot be quantified. Therefore, aiming at these problems, this paper designs a high embedding rate and tamper-proof watermarking scheme. We employ wet paper coding (WPC), in which important parameters are regarded as wet blocks and the remaining unimportant parameters are regarded as dry blocks in the model. To obtain the important parameters more easily, we propose an optimized probabilistic selection strategy (OPSS). OPSS defines the unimportant-level function and sets the importance threshold to select the important parameter positions and to ensure that the original function is not affected after the model parameters are changed. We regard important parameters as an unmodifiable part, and only modify the part that includes the unimportant parameters. We selected the MNIST, CIFAR-10, and ImageNet datasets to test the performance of the model after adding a watermark and to analyze the fidelity, robustness, embedding rate, and comparison schemes of the model. Our experiment shows that the proposed scheme has high fidelity and strong robustness along with a high embedding rate and the ability to prevent malicious tampering.

With the widespread use of deep-learning models in production environments, the value of deep-learning models has become more prominent. The key issues are the rights of the model trainers and the security of the specific scenarios using the models. In the commercial domain, consumers pay different fees and have access to different levels of services. Therefore, dividing the model into several shadow models with multiple weights is necessary. When holders want to use the model, they can recover the model whose performance corresponds to the number and weights of the collected shadow models so that access to the model can be controlled progressively, i.e., progressive recovery is significant. This paper proposes a neural network model secret sharing scheme (NNSS) with multiple weights for progressive recovery. The scheme uses Shamir’s polynomial to control model parameters’ sharing and embedding phase, which in turn enables hierarchical performance control in the secret model recovery phase. First, the important model parameters are extracted. Then, effective shadow parameters are assigned based on the holders’ weights in the sharing phase, and t shadow models are generated. The holders can obtain a sufficient number of shadow parameters for recovering the secret parameters with a certain probability during the recovery phase. As the number of shadow models obtained increases, the probability becomes larger, while the performance of the extracted models is related to the participants’ weights in the recovery phase. The probability is proportional to the number and weights of the shadow models obtained in the recovery phase, and the probability of the successful recovery of the shadow parameters is 1 when all t shadow models are obtained, i.e., the performance of the reconstruction model can reach the performance of the secret model. A series of experiments conducted on VGG19 verify the effectiveness of the scheme.