摘要：
The ARX-based lightweight block cipher is widely used in resource-constrained IoT devices due to fast , simple operation of software and hardware platforms. However, there are three weaknesses to ARX-based lightweight block ciphers. Firstly, only half of the data can be changed in one round. Secondly, traditional ARX-based lightweight block ciphers are static structures, which provide limited security. Thirdly, it has poor diffusion when the initial plaintext and key are all 0 or all 1. This paper proposes a new dynamic ARX-based lightweight block cipher to overcome these weaknesses, called DABC. DABC can change all data in one round, which overcomes the first weakness. This paper combines the key and the generalized two-dimensional cat map to construct a dynamic permutation layer P1, which improves the uncertainty between different rounds of DABC. The non-linear component of the round function alternately uses NAND gate and , gate to increase the complexity of the attack, which overcomes the third weakness. Meanwhile, this paper proposes the round-based architecture of DABC and conducted ASIC and FPGA implementation. The hardware results show that DABC has less hardware resource and high throughput. Finally, the safety evaluation results show that DABC has a good avalanche effect and security.
期刊：
European Journal of Remote Sensing,2023年56(1) ISSN：1129-8596
通讯作者：
Wan, XQ
作者机构：
[Wan, Xiaoqing] Hengyang Normal Univ, Coll Comp Sci & Technol, Hengyang, Peoples R China.;[Chen, Shuanghao] Zhengzhou Univ, Coll Comp & Engn, Zhengzhou, Peoples R China.
通讯机构：
[Wan, XQ ] H;Hengyang Normal Univ, Coll Comp Sci & Technol, Hengyang, Peoples R China.
关键词：
Classification;hyperspectral image;multiple strategy fusion;multi-scale block local binary pattern;edge-preserving filtering
摘要：
In this paper, a multi-strategy fusion (MSF) framework, based on improved MBLBP and bi-exponential edge-preserving smoother (BEEPS), is proposed for hyperspectral image (HSI) classification. First, MBLBP operator is adopted to characterize the overall structural information of HSI, where the averaging strategy allocates same weights for the pixels in a local sub-region, so that the edges tend to be blurred due to being isotropic. To solve this question, the steering kernel is first introduced into MBLBP for learning the local structure prior of HSI. Then, a support vector machine classifier is used to calculate the soft classified probabilities of pixels. Furthermore, BEEPS is adopted to smooth the soft classified probabilities maps in the post-processing stage, and the purpose is to further improve classification accuracy of HSI by considering context-aware information for each class label. Experiments are performed on three real hyperspectral datasets, namely, Indian Pines, KSC, and Houston 2013, only 1%, 6, and 5 labeled samples are randomly selected for training, the overall accuracy(kappa) obtained by MSF is 99.47%(99.40), 99.52%(99.47), and 94.25%(93.78), respectively, which is far better than the contrast methods.
摘要：
Differential analysis is a vital tool for evaluating the security of cryptography algorithms. There has been a growing interest in the differential distinguisher based on deep learning. Various neural network models have been created to increase the accuracy of distinguishing between ciphertext and random sequences. However, few studies have focused on differential analysis at the design stage of cryptographic algorithms. This paper presents an appropriate model for differential analysis of block ciphers. The model is similar to multilayer perceptron (MLP) models in simplicity and clarity. It also introduces a shortcut connection that enables one to learn more information about the differential analysis dataset. The model is used to predict the minimum number of active S-boxes (AS), linking differential analysis results to algorithm features. This model and two classical neural network models are compared under fair experimental conditions. The findings indicate that our model predicts the AS values with an accuracy of 97%. It can effectively predict the results of differential analysis. In addition, the differential analysis dataset is constructed for SPN structure cryptographic algorithms. It can be used for further differential analysis studies based on deep learning.
摘要：
Image transmission is happening more frequently in this era of technologically sophisticated digital information. Additionally, more individuals are becoming aware of its importance. In order to secure images, many academics are participating in research, which is advantageous for guaranteeing data security. In order to strengthen the security of images during transmission, we have investigated new encryption algorithms to guarantee this. First, a current representing the Lorenz chaotic system is introduced into the neuron model. The neuron model generates sequences after receiving the current signal. The next move is made as the current shifts depending on whether the resulting sequences are chaotic or not. If so, the subsequent operation is carried out; otherwise, the current is altered until chaotic sequences are produced. Second, a global scrambling with de-duplication technique is used to scramble the image using the resulting chaotic sequences. To complete the dislocation effect, the Latin square is used to dislocate the image after the initial dislocation. Fourth, the image that has been scrambled is subjected to two rounds of additive mode diffusion. They are diffusion in the forward additive mode and diffusion in the inverse additive mode. Lastly, to improve the diffusion effect, the image is diffused in the finite domain. Eventually, the encrypted image is obtained. After evaluation tests and comparison with related literature, it can be found that the algorithm of this study has certain advantages. Also, the resistance to attack is good. It can protect the security of the image.
通讯机构：
[Huihuang Zhao] C;College of Computer Science and Technology, Hengyang Normal University, Hengyang 421002, China<&wdkj&>Hunan Provincial Key Laboratory of Intelligent Information Processing and Application, Hengyang 421002, China
关键词：
VStyclone;Voice clone;Efficient tone extractor;Style synthesizer;Transformer;Vocoder
摘要：
This paper proposes a novel Chinese speech cloning model named VStyclone, which consists of three stages: multi-speaker training, target speaker encoding, and target speaker synthesis. In this work, we design an efficient tone extractor, which can reallocate resources to the sequences of log-mel spectrogram frames obtained from multiple speakers’ speech, thus allowing the network to learn multiple speakers’ features differently. This approach allows the network to focus more on the voice features of the target speaker and extract the target features accurately. To cluster the voices of the same speaker and sparse the voices of different speakers, we build an optimal softmax loss to optimize the model. Then, we develop a style synthesizer, which adopts the idea of transformer instead of recurrent neural network, so that the model can not only process text information in parallel, but also improve the model's ability to process long-distance contextual information. Meanwhile, we embed a style extraction module in the style synthesizer to dynamically capture style ranges in an unsupervised manner. In addition, the VStyclone model uses generative adversarial networks as the base generation model of the vocoder to improve the generation speed, which runs 1.2 times faster than the real-time generation speed on CPU, and finally the VStyclone model obtains the SOTA effect.
通讯机构：
[Mugang Lin] C;College of Computer Science and Technology, Hengyang Normal University, Hengyang 421002, China<&wdkj&>Hunan Provincial Key Laboratory of Intelligent Information Processing and Application, Hengyang 421002, China
摘要：
The graph autoencoder (GAE) is a powerful graph representation learning tool in an unsupervised learning manner for graph data. However, most existing GAE-based methods typically focus on preserving the graph topological structure by reconstructing the adjacency matrix while ignoring the preservation of the attribute information of nodes. Thus, the node attributes cannot be fully learned and the ability of the GAE to learn higher-quality representations is weakened. To address the issue, this paper proposes a novel GAE model that preserves node attribute similarity. The structural graph and the attribute neighbor graph, which is constructed based on the attribute similarity between nodes, are integrated as the encoder input using an effective fusion strategy. In the encoder, the attributes of the nodes can be aggregated both in their structural neighborhood and by their attribute similarity in their attribute neighborhood. This allows performing the fusion of the structural and node attribute information in the node representation by sharing the same encoder. In the decoder module, the adjacency matrix and the attribute similarity matrix of the nodes are reconstructed using dual decoders. The cross-entropy loss of the reconstructed adjacency matrix and the mean-squared error loss of the reconstructed node attribute similarity matrix are used to update the model parameters and ensure that the node representation preserves the original structural and node attribute similarity information. Extensive experiments on three citation networks show that the proposed method outperforms state-of-the-art algorithms in link prediction and node clustering tasks.
关键词：
Deformation;Windows;Object detection;Education and training;Image processing;Feature extraction;Cameras;Distortion;Head;Data modeling
摘要：
Retail product detection in fisheye camera capture scenes frequently suffers from excessive object occlusion and deformation, as well as difficulty in distinguishing products with small fine-grained differences, so accurately classifying and localizing products in these images presents a challenge for computer vision. We propose an efficient product detection network called EPformer by fusing a visual transformer and convolutional neural network to reliably detect retail products in fisheye images. We employ a shifted window strategy for feature information interaction across windows to more precisely detect products due to the issue of dense occlusion of products. To address the issue of excessive product deformation brought on by fisheye cameras, we develop a deformation image processing module without explicit correction and embed it into the path aggregation network structure. This enables the model to efficiently capture product geometric changes and conduct feature fusion. To address the issue of differentiating fine-grained products, we design an effective coordinate squeeze-excitation (ECSE) attention module that can capture the fine-grained texture and boundary information differences between individuals in terms of spatial and channel relationships. The inability to differentiate fine-grained products can be solved by training the ECSE module in tandem with the decoupled head. The experimental results demonstrate that EPformer is a potent product detection model with a 4.9% higher mean average precision than the state-of-the-art method (YOLOX) on the fisheye product image dataset. In addition, the EPformer model can effectively detect products in fisheye images on the Jeston Xavier NX embedded device to meet the application requirements in realistic scenarios.
作者机构：
[Zhu, Xianyou; Fan, Liu] Hengyang Normal Univ, Coll Comp Sci & Technol, Hengyang 421010, Peoples R China.;[Wang, Lei; Fan, Liu] Changsha Univ, Inst Bioinformat Complex Network Big Data, Changsha 410022, Peoples R China.;[Wang, Lei] Changsha Univ, Big Data Innovat & Entrepreneurship Educ Ctr Huna, Changsha 410022, Peoples R China.;[Zhu, Xianyou] Hengyang Normal Univ, Coll Comp Sci & Technol, Hengyang 421010, Peoples R China.;[Wang, Lei] Changsha Univ, Inst Bioinformat Complex Network Big Data, Changsha 410022, Peoples R China.
通讯机构：
[Zhu, XY ; Wang, L ] ;Hengyang Normal Univ, Coll Comp Sci & Technol, Hengyang 421010, Peoples R China.;Changsha Univ, Inst Bioinformat Complex Network Big Data, Changsha 410022, Peoples R China.;Changsha Univ, Big Data Innovat & Entrepreneurship Educ Ctr Huna, Changsha 410022, Peoples R China.
摘要：
Microbes are intimately tied to the occurrence of various diseases that cause serious hazards to human health, and play an essential role in drug discovery, clinical application, and drug quality control. In this manuscript, we put forward a novel prediction model named MDASAE based on a stacked autoencoder (SAE) with multi-head attention mechanism to infer potential microbe-drug associations. In MDASAE, we first constructed three kinds of microbe-related and drug-related similarity matrices based on known microbe-disease-drug associations respectively. And then, we fed two kinds of microbe-related and drug-related similarity matrices respectively into the SAE to learn node attribute features, and introduced a multi-head attention mechanism into the output layer of the SAE to enhance feature extraction. Thereafter, we further adopted the remaining microbe and drug similarity matrices to derive inter-node features by using the Restart Random Walk algorithm. After that, the node attribute features and inter-node features of microbes and drugs would be fused together to predict scores of possible associations between microbes and drugs. Finally, intensive comparison experiments and case studies based on different well-known public databases under 5-fold cross-validation and 10-fold cross-validation respectively, proved that MDASAE can effectively predict the potential microbe-drug associations.
摘要：
The main challenges in face swapping are the preservation and adaptive superimposition of attributes of two images. In this study, the Face Swapping Attention Network (FSA-Net) is proposed to generate photoreal-istic face swapping. The existing face-swapping methods ignore the blending attributes or mismatch the facial keypoint (cheek, mouth, eye, nose, etc.), which causes artifacts and makes the generated face silhouette non-realistic. To address this problem, a novel reinforced multi-aware attention module, referred to as RMAA, is proposed for handling facial fusion and expression occlusion flaws. The framework includes two stages. In the first stage, a novel attribute encoder is proposed to extract multiple levels of target face attributes and integrate identities and attributes when synthesizing swapped faces. In the second stage, a novel Stochastic Error Refinement (SRE) module is designed to solve the problem of facial occlusion, which is used to repair occlusion regions in a semi-supervised way without any post-processing. The proposed method is then compared with the current state-of-the-art methods. The obtained results demonstrate the qualitative and quantitative outperformance of the proposed method. More details are provided at the footnote link and at https://sites.google.com/view/fsa-net-official.
关键词：
Internet of Things (IoT);involutive;lightweight block cipher;permutation;S-box;security
摘要：
Nowadays, the use of the Internet of Things has reached a commanding height in a new round of economic and technological upsurge. Its data transmission security has attracted much attention. It is well known that substitution permutation networks (SPNs) ciphers with high diffusion are not advantageous in unified encryption and decryption circuits with extremely resources constrained. Although some research has been carried out to address this issue, there are still insufficiencies. In this article, we propose a new 64-bit lightweight block cipher based on SPN named IVLBC, whose key allows 80 and 128 bits. The components of IVLBC are involutions. In particular, we propose a Feistel with tree structure to obtain a compact and involutive S-box. Also, the nibble-based involutive permutation is proposed to obtain the involutive permutation. Decryption can reuse encrypted code and circuitry in both software and hardware implementations. We prove that the costs of IVLBC are less than PRESENT, PRINCE, Midori, I-PRESENTTM, CRAFT, etc., in unified encryption and decryption circuits. In addition, we conduct other performance tests on IVLBC such as the differential attack, linear attack, integral attack, algebraic attack, invariant attacks, etc.
摘要：
The number of industrial Internet of Things (IoT) users is increasing rapidly. Lightweight block ciphers have started to be used to protect the privacy of users. Hardware-oriented security design should fully consider the use of fewer hardware devices when the function is fully realized. Thus, this paper designs a lightweight block cipher IIoTBC for industrial IoT security. IIoTBC system structure is variable and flexibly adapts to nodes with different security requirements. This paper proposes a 4x4 S-box that achieves a good balance between area overhead and cryptographic properties. In addition, this paper proposes a preprocessing method for 4x4 S-box logic gate expressions, which makes it easier to obtain better area, running time, and power data in ASIC implementation. Applying it to 14 classic lightweight block cipher S-boxes, the results show that is feasible. A series of performance tests and security evaluations were performed on the IIoTBC. As shown by experiments and data comparisons, IIoTBC is compact and secure in industrial IoT sensor nodes. Finally, IIoTBC has been implemented on a temperature state acquisition platform to simulate encrypted transmission of temperature in an industrial environment.
通讯机构：
[Li, QP ] H;Hengyang Normal Univ, Coll Comp Sci & Technol, Hengyang 421002, Peoples R China.;Hunan Prov Key Lab Intelligent Informat Proc & App, Hengyang 421002, Peoples R China.
摘要：
The graph G of order n is an L-borderenergetic graph which means it has the same Laplacian energy as the complete graph Kn. In this paper, we find that the combination of complete bi-partite graphs and stars can construct infinite numbers of infinite classes L-borderenergetic graphs. We give two infinite numbers of infinite classes L-borderenergetic graphs and two infinite classes L-borderenergetic graphs under the operators union, join and their mixed. This research could provide experience for further study the structural characteristics of L-borderenergetic graphs.
通讯机构：
[Lang Li] C;College of Computer Science and Technology, Hengyang Normal University, Hengyang, China<&wdkj&>Hunan Provincial Key Laboratory of Intelligent Information Processing and Application, Hengyang Normal University, Hengyang, China
关键词：
internet of things;5G;dynamic S-box;bit-slice technology;lightweight block cipher
摘要：
IoT devices have been widely used with the advent of 5G. These devices contain a large amount of private data during transmission. It is primely important for ensuring their security. Therefore, we proposed a lightweight block cipher based on dynamic S-box named DBST. It is introduced for devices with limited hardware resources and high throughput requirements. DBST is a 128-bit block cipher supporting 64-bit key, which is based on a new generalized Feistel variant structure. It retains the consistency and significantly boosts the diffusion of the traditional Feistel structure. The SubColumns of round function is implemented by combining bit-slice technology with subkeys. The S-box is dynamically associated with the key. It has been demonstrated that DBST has a good avalanche effect, low hardware area, and high throughput. Our S-box has been proven to have fewer differential features than RECTANGLE S-box. The security analysis of DBST reveals that it can against impossible differential attack, differential attack, linear attack, and other types of attacks.
摘要：
The accurate and automatic segmentation of retinal vessels from fundus images is critical for the early diagnosis and prevention of many eye diseases, such as diabetic retinopathy (DR). Existing retinal vessel segmentation approaches based on convolutional neural networks (CNNs) have achieved remarkable effectiveness. Here, we extend a retinal vessel segmentation model with low complexity and high performance based on U-Net, which is one of the most popular architectures. In view of the excellent work of depth-wise separable convolution, we introduce it to replace the standard convolutional layer. The complexity of the proposed model is reduced by decreasing the number of parameters and calculations required for the model. To ensure performance while lowering redundant parameters, we integrate the pre-trained MobileNet V2 into the encoder. Then, a feature fusion residual module (FFRM) is designed to facilitate complementary strengths by enhancing the effective fusion between adjacent levels, which alleviates extraneous clutter introduced by direct fusion. Finally, we provide detailed comparisons between the proposed SepFE and U-Net in three retinal image mainstream datasets (DRIVE, STARE, and CHASEDB1). The results show that the number of SepFE parameters is only 3% of U-Net, the Flops are only 8% of U-Net, and better segmentation performance is obtained. The superiority of SepFE is further demonstrated through comparisons with other advanced methods.
摘要：
In this paper, a lossless image compression and encryption algorithm combining JPEG-LS, neural networks and hyperchaotic mapping is proposed to protect the privacy of digital images and reduce data storage space. Firstly, we design a new 2-Dimensional Logistic-Like Hyperchaotic Map (2DLLHM), which has more complex dynamics than some existing known chaotic systems, and can be used to build a good pseudorandom sequence generator. Secondly, to compress images efficiently, we design a new pixel predictor by combining the MED (Median Edge Detector) of JPEG-LS with MLP (Multilayer Perceptron). This predictor is called MMP. The MMP can effectively improve the prediction effect of edge texture area. On this basis, a threshold segmentation method is proposed. The method combined with MMP, run-length coding and Huffman coding can further improve the image compression ratio. Finally, to avoid some of the existing weak encryption designs, we construct a multi-round nonlinear diffusion structure with more excellent diffusion performance. Experiments show that the algorithm achieves a good compression ratio and can resist brute force attacks, statistical attacks, chosen-plaintext attacks and chosen-ciphertext attacks.
关键词：
SAND;ARX-Based lightweight block cipher;High -diffusion architecture;Mixed integer linear programming
摘要：
The development of ARX-based lightweight block ciphers has been plagued by the difficulty of theoretical security analysis. SAND solves this problem better by obtaining an equivalent representation based on a synthetic S-box. This paper analyzed SAND in terms of diffusivity and found that it can be optimized. SAND has the issue of slow diffusion after the initial plaintext and key are all 0. On the other hand, it takes at least 11 rounds for SAND to reach full diffusion without AddRoundKey. Thus, this paper proposes a high-diffusion architecture SAND-2 to address the above issues. Firstly, issue 1 is solved by replacing the AND operation with a NAND operation and calling the round function dynamically. Then, in order to solve issue 2, P1 and P2 permutations are introduced into G0 and G1 , respectively. The full diffusion speed of SAND-2 is 63.7% increased compared to SAND. In addition, the comparison results of hardware indicators show that the hardware resources of SAND-2 are slightly lower, and the throughput is 10% higher than SAND. Finally, the security analysis shows that SAND-2 reaches the upper bound of the resisting differential analysis in fewer rounds.
通讯机构：
[Huihuang Zhao] C;College of Computer Science and Technology, Hengyang Normal University, Hengyang, 421002, China<&wdkj&>Hunan Provincial Key Laboratory of Intelligent Information Processing and Application, Hengyang, 421002, China
摘要：
Cartoonization is a widely practiced art form that has been integrated into every aspect of our life. Although cartoonization has made significant progress, it is still challenging to produce high-quality graphics. In this paper, a new model named Convolutional Block Attention Generative Adversarial Networks (CBA-GAN) is proposed to transform real photos into cartoonish images. The proposed method can multiply the feature images of the input image to achieve adaptive feature optimization, and can flexibly adjust the proportion of edge, texture and smoothness in the image effect, without generating redundant edges, and can better deal with shadows in the image. The experimental data set consists of content images (real scenes or photos) and style images (cartoon images), among which the content images are mainly divided into face photos, animals, food, scenes and so on. The experimental results on different types of images show that the performance of this method is better than the existing three representative methods, and it has good robustness. At the same time, the style image data set in this paper comes from animation video, therefore this method can be easily transferred to the cartoon of video.
摘要：
Researches have demonstrated that microorganisms are indispensable for the nutrition transportation, growth and development of human bodies, and disorder and imbalance of microbiota may lead to the occurrence of diseases. Therefore, it is crucial to study relationships between microbes and diseases. In this manuscript, we proposed a novel prediction model named MADGAN to infer potential microbe-disease associations by combining biological information of microbes and diseases with the generative adversarial networks. To our knowledge, it is the first attempt to use the generative adversarial network to complete this important task. In MADGAN, we firstly constructed different features for microbes and diseases based on multiple similarity metrics. And then, we further adopted graph convolution neural network (GCN) to derive different features for microbes and diseases automatically. Finally, we trained MADGAN to identify latent microbe-disease associations by games between the generation network and the decision network. Especially, in order to prevent over-smoothing during the model training process, we introduced the cross-level weight distribution structure to enhance the depth of the network based on the idea of residual network. Moreover, in order to validate the performance of MADGAN, we conducted comprehensive experiments and case studies based on databases of HMDAD and Disbiome respectively, and experimental results demonstrated that MADGAN not only achieved satisfactory prediction performances, but also outperformed existing state-of-the-art prediction models.
作者机构：
[Yang, Yufei; Hu, Boxia] Hunan Univ, Sch Math, Changsha 410082, Peoples R China.;[Hu, Boxia] Hengyang Normal Univ, Coll Math & Stat, Hengyang 421002, Peoples R China.;[Ouyang, Ze; Sun, Yaqi; Zhang, Feng] Hengyang Normal Univ, Coll Comp Sci & Technol, Hengyang 421002, Peoples R China.;[Yang, Yufei] Changsha Univ, Sch Math, Changsha 410022, Peoples R China.
关键词：
Rain removal;edge optimization;robust;Unet plus plus
摘要：
Image deraining has become a hot topic in the field of computer vision. It is the process of removing rain streaks from an image to reconstruct a high-quality background. This study aims at improving the performance of image rain streak removal and reducing the disruptive effects caused by rain. To better fit the rain removal task, an innovative image deraining method is proposed, where a kernel prediction network with Unet++ is designed and used to filter rainy images, and rainy-day images are used to estimate the pixel-level kernel for rain removal. To minimize the gap between synthetic and real data and improve the performance in real rainy image handling, a loss function and an effective data optimization method are suggested. In contrast with other methods, the loss function consists of Structural Similarity Index loss, edge loss, and L1 loss, and it is adopted to improve performance. The proposed algorithm can improve the Peak Signal-to-Noise ratio by 1.3% when compared to conventional approaches. Experimental results indicate that the proposed method can achieve a better efficiency and preserve more image structure than several classical methods.
