In network analysis, methods for identifying a community structure of ten involve optimizing a specific objective function to achieve a single optimal allocation from network nodes to communities. In practice, however, we often encounter multiple division schemes with high-quality scores close to the overall optimum. An accurate depiction of the community structure is more appropriately achieved by a series of high-quality division schemes rather than relying solely on a single optimal solution. However, such a collection of network divisions may be challenging to interpret, as its size may rapidly expand to hundreds or even thousands. To this end, we propose a representative community detection algorithm for attribute networks. By clustering similar network partitions and selecting representative partitions from each cluster, we can comprehensively reveal the diversity of network community structures and provide partition results with a more global perspective. Network partitioning experiments on natural and artificial datasets demonstrate that our proposed method performs better than advanced methods.

The unsupervised attribute graph embedding technique aims to learn low-dimensional node embedding using neighborhood topology and attribute information under unlabeled data. Current unsupervised models are mostly based on graph self-encoders, but full-batch training limits the scalability of the model and ignores attribute integrity when reconstructing the topology. In order to solve the above problems while considering the unsupervised learning of the model and full use of node information, this paper proposes a graph neural network architecture based on a graph self-encoder to capture the nonlinearity of the attribute graph data, and an attribute graph embedding algorithm that explicitly models the influence of neighborhood information using a multi-level attention mechanism. Specifically, the proposed algorithm fuses topology information and attribute information using a lightweight sampling strategy, constructs an unbiased graph self-encoder on the sampled graph, implements topology aggregation and attribute aggregation, respectively, models the correlation between topology embedding and attribute embedding, and considers multi-level loss terms.

In network analysis, methods for identifying a community structure of ten involve optimizing a specific objective function to achieve a single optimal allocation from network nodes to communities. In practice, however, we often encounter multiple division schemes with high-quality scores close to the overall optimum. An accurate depiction of the community structure is more appropriately achieved by a series of high-quality division schemes rather than relying solely on a single optimal solution. However, such a collection of network divisions may be challenging to interpret, as its size may rapidly expand to hundreds or even thousands. To this end, we propose a representative community detection algorithm for attribute networks. By clustering similar network partitions and selecting representative partitions from each cluster, we can comprehensively reveal the diversity of network community structures and provide partition results with a more global perspective. Network partitioning experiments on natural and artificial datasets demonstrate that our proposed method performs better than advanced methods.

Permutation is a commonly used operation in image encryption schemes. Many schemes adopt a separate row and column permutation to increase the encryption efficiency while ignoring the security. This paper proposes an efficient known-plaintext attack (KPA) for row-column-based permutation. A special ID method based on the Pearson correlation coefficient is proposed to label each column or row. Only one pair of known plaintext-ciphertext images is enough to determine the permutation rules completely. With this attack method for permutation, a classic permutation-then-XOR image encryption scheme is broken with only two known plaintext-ciphertext image pairs. A numerical example of the proposed attack is provided to show the process intuitively and clearly. In addition, the cryptanalyses of two related image ciphers are introduced. Detailed theoretical derivations and extensive experiments confirmed the feasibility and efficiency of the proposed attacks. The related MATLAB codes are publicly available and can be found online.