Journal of King Saud University-Computer and Information Sciences最新文献

In the context of the rapid development of Internet of Things (IoT) technology and the extensive proliferation of the global Internet, the authenticity of data has become a focal point of societal demand. It plays a decisive role in enhancing the quality of decision-making and operational efficiency. However, the storage and authenticity verification of large-scale IoT real-time data present unprecedented technical challenges. Faced with the inherent data security risks of traditional centralized cloud storage, blockchain technology reveals its unique potential for solutions with its inherent immutability and decentralization. Nevertheless, current blockchain-based data storage solutions are still restricted by high costs and inefficiency. To address these challenges, this paper innovatively proposes the BI-TSFID framework, which leverages the benefits of Ethereum and IPFS and optimizes the Merkle Tree structure and verification mechanisms. The BI-TSFID framework adopts a strategy of on-chain data summary storage and off-chain computation. This approach provides IoT with efficient and reliable data storage, reduces operational costs, and simplifies the verification process. This research has improved the data computation efficiency by refining the structure of the Merkle Tree and analyzed its optimal branch number. Additionally, the study introduces a sampling-based data integrity verification method that significantly reduces resource consumption during the verification process. Experimental results show that the solutions proposed in this paper effectively enhance the efficiency and security of IoT data management and provide valuable guidance for the theory and practice of real-time data storage and verification, further promoting the development and innovation in the related technological fields.

Infrared and visible image fusion is an effective solution for image quality enhancement. However, conventional fusion models require the decomposition of source images into image blocks, which disrupts the original structure of the images, leading to the loss of detail in the fused images and making the fusion results highly sensitive to matching errors. This paper employs Convolutional Sparse Representation (CSR) to perform global feature transformation on the source images, overcoming the drawbacks of traditional fusion models that rely on image decomposition. Inspired by neural networks, a multi-layer CSR model is proposed, which involves five layers in a forward-feeding manner: two CSR layers acquiring sparse coefficient maps, one fusion layer combining sparse maps, and two reconstruction layers for image recovery. The dataset used in this paper comprises infrared and visible images selected from public dataset, as well as registered images collected by an actual Unmanned Aerial Vehicle (UAV). The source images contain ground targets, marine targets, and natural landscapes. To validate the effectiveness of the proposed image fusion model in this paper, comparative analysis is conducted with state-of-the-art (SOTA) algorithms. Experimental results demonstrate that the proposed fusion model outperforms other state-of-the-art methods by at least 10% in SF, EN, MI and $Q^{AB/F}$ fusion metrics in most image fusion cases, thereby affirming its favorable performance.

Detecting misbehavior in social networks is essential for maintaining trust and reliability in online communities. Traditional methods of identification often rely on individual attributes or structural network properties, which may overlook subtle or complex misbehavior patterns. This paper introduces a novel approach called OCMLMD that leverages network overlapping community structure and machine learning techniques to detect misbehavior. Our method combines graph-based analyses of network topology with state-of-theart machine learning algorithms to identify suspicious behavior indicative of misbehavior. Specifically, we target nodes that belong to multiple communities or exhibit weak connections within their community, utilizing a novel metric for selecting overlapping nodes. Additionally, we develop a machine learning model trained on relevant attributes extracted from social network data to detect misbehavior accurately. Extensive experiments on synthetic and real-world social network datasets demonstrate the superior performance of OCMLMD compared to baseline methods. Overall, our proposed approach offers a promising solution to the challenge of detecting misbehavior in social networks.

Addressing the quintessential challenge of local feature matching in computer vision, this study introduces a novel fast sparse seed graph structure named LightSGM. This structure aims to refine the characterization of graph features while minimizing superfluous connections. Initially, a subset of high-quality seed feature points is curated using a confidence filter. Subsequently, keypoint features are assimilated into this seed set via graph pooling, and the composite features are further processed through a memory and computation-efficient seed transformer to capture rich contextual information about the keypoints. The seed feature points are then relayed back to the original keypoints using an inverse process known as graph unpooling. The paper also introduce an adaptive mechanism to determine the optimal number of model layers based on the intricacy of matching image pairs. A Matching Point Prediction Header is employed to extract the final set of matching points. Through extensive experimentation on image matching and position estimation, LightSGM has demonstrated its prowess in delivering competitive matching accuracy while maintaining a balance with real-time processing capabilities.

In drone aerial target detection tasks, a high proportion of small targets and complex backgrounds often lead to false positives and missed detections, resulting in low detection accuracy. To improve the accuracy of the detection of small targets, this study proposes two improved models based on YOLOv8s, named IMCMD_YOLOv8_small and IMCMD_YOLOv8_large. Each model accommodates different application scenarios. First, the network structure was optimized by removing the backbone P5 layer used to detect large targets and merging the P4, P3, and P2 layers, which are better suited for detecting medium and small targets; P3 and P2 serve as detection heads to focus more on small targets. Subsequently, the coordinate attention mechanism is integrated into the backbone’s C2f, to create a C2f_CA module that enhances the model’ s focus on key information and secures a richer flow of gradient information. Subsequently, a multiscale attention feature fusion module was designed to merge the shallow and deep features. Finally, a Dynamic Head was introduced to unify the perception of scale, space, and tasks, further enhancing the detection capability for small targets. Experimental results on the VisDrone2019 dataset demonstrated that, compared with YOLOv8s, IMCMD_YOLOv8_small achieved improvements of 7.7% and 5.1% in [email protected] and [email protected]:0.95, respectively, with a 73.0% reduction in the parameter count. The IMCMD_YOLOv8_large model showed even more significant improvements in these metrics, reaching 10.8% and 7.3%, respectively, with a 47.7% reduction in the parameter count, displaying superior performance in small target detection tasks. The improved models not only enhanced the detection accuracy but also achieved model lightweighting, thereby proving the effectiveness of the improvement strategies and showcasing superior performance compared with other classic models.

Researching infrared adversarial attacks is crucial for ensuring the safe deployment of security-sensitive systems reliant on infrared object detectors. However, current research on infrared adversarial attacks mainly focuses on pedestrian detection tasks. Due to the complex shape and structure of vehicles and the changing working conditions, adversarial attack in infrared vehicle detection pose challenges like difficult multi-angle attack, poor physical transferability, and weak environmental adaptation. This paper proposed Leaf-like Mask Bar Code (LMBC), a novel adversarial attack method for multi-angle physical black-box attack on infrared detectors. Inspired by natural leaf structures, a mask was designed to restrict the adversarial patch contour. Then, adversarial parameters of the patches (angle, sparsity, and position) were optimized using the Genetic Algorithm with Multi-segment (GAM). Moreover, leaf-like structures in physical adversarial patches were constructed using suitable infrared coating materials. deploying them at multiple angles. Experimental results demonstrated LMBC’s efficacy, paralyzing the infrared vehicle detector with an Average Precision (AP) as low as 33.7% and an average Attack Success Rate (ASR) as high as 92.9% across a distance of 2.4m 4.2 m and angles of 0° 360°. Moreover, LMBC’s adversarial patches transferred to mainstream detectors (e.g., Faster RCNN, Yolov3, etc.) and pedestrian detection tasks.

Detecting variations in dialects within a language can be challenging, particularly in regions with rich linguistic diversity like Saudi Arabia. To our knowledge, no prior attempts have been made to develop a multimodal, audio–textual framework for Saudi dialect detection. The current approaches often concentrate on detecting dialects only based on audio or textual data, which fails to capture the complex relationship between both modalities. In this paper, we propose a novel Multimodal Framework, called MF-Saudi, for Saudi dialect detection. The framework consists of three main components: (1) a pretrained BERT encoder for extracting and encoding textual information; (2) an acoustic model for representing audio signals and fusing them with textual information via the fusion layer; and (3) an alignment learning module to develop meaningful representations that capture the complexities of audio–text relationships, resulting in improved dialect detection. We conduct empirical evaluations on a real-world dataset, demonstrating that our solution outperforms some of the state-of-the-art baseline methods. The experiment’s code can be found here: https://github.com/raed19/MF-Saudi.

The widespread use of spatial location-based services not only provides considerable convenience, but also exposes the downsides of location privacy leakage. Most of the existing user-side location privacy protection techniques are limited to planar locations. However, the extensive use of aircraft, sensor equipment and acquisition devices with positioning functions promotes the urgency of protecting the privacy of 3D spatial locations. Therefore, this study suggests a local differential privacy protection approach for 3D spatial locations. A 3D spatial decomposition and Hilbert encoding method are designed to reduce the 3D location data into one-dimensional encoding. The optimized random response mechanism was utilized to perturb the dimensional-reduced location encoding, which not only achieves user-side location privacy protection but also improves the accuracy of aggregated data on the server-side. Experiments on the real spatial location datasets show that the suggested method can reduce spatial location service quality loss, maintain the availability of perturbed spatial location and improve the operation efficiency of the spatial location perturbation algorithm.

Deep learning technologies have led to substantial breakthroughs in the field of biomedical image analysis. Accurate brain tumor segmentation is an essential aspect of treatment planning. Radiologists agree that manual segmentation is a difficult and time-consuming task that frequently causes delays in the diagnosing process. While U-Net-based methods have been widely used for brain tumor segmentation, many challenges persist, particularly when dealing with tumors of varying sizes, locations, and shapes. Additionally, segmenting tumor regions with structures requires a comprehensive model, which can increase computational complexity and potentially cause gradient vanishing issues. This study presents a novel method called 3D Guided Attention-based deep Inception Residual U-Net (GAIR-U-Net) to address these challenges. This model combines attention mechanisms, an inception module, and residual blocks with dilated convolution to enhance feature representation and spatial context understanding. The backbone of the model is the U-Net model, which leverages the power of inception and residual connections to capture intricate patterns and hierarchical features while expanding the model’s width in three-dimensional space without significantly increasing computational complexity. The attention mechanisms play a role in focusing on important regions and areas while downgrading irrelevant details. The dilated convolutions in the network help in learning both local and global information, improving accuracy and adaptability in segmenting tumors. All the experiments in this study were carried out on multimodal MRI scans that include (T1-weighted, T1-ce, T2-weighted, and FLAIR sequences) from the BraTS 2020 dataset. The presented model is trained and tested on the same dataset, which exhibited promising performance compared to previous methods. On the BraTS 2020 validation dataset, the proposed model obtained a dice score of 0.8796, 0.8634, and 0.8441 for whole tumor (WT), tumor core (TC), and enhancing tumor (ET), respectively. These results demonstrate the model’s efficacy in precisely segmenting brain tumors across various modalities. Comparative analyses underscore the model’s versatility in handling tumor shape variations, size, and location, making it a promising solution for clinical applications.

Accurate assessment of high-density underwater fish resources is vital to the aquaculture industry. It is directly related to the formulation of fishery insurance strategies and the implementation of breeding plans. However, accurately counting fish in high-density environments becomes challenging due to the uneven distribution of fish density and individual fish’s different sizes and postures. To break through this technical bottleneck, we developed an advanced adaptive density-guided high-density fish counting network. In detail, first of all, the network adopts a multi-layer feature fusion structure similar to UNet, which significantly enhances the matching between fish targets of different scales and feature pyramid levels, effectively alleviating the problems caused by scale changes and morphological deformations. Secondly, the network also introduces a density-guided adaptive selection module, which can intelligently judge the applicability of Convolutional Neural Network and Transformer blocks in different density areas, thereby achieving robust information transfer and interaction between blocks. Finally, to verify the effectiveness of this method, we also specially constructed two high-density data sets: a simulated high-density underwater fish image data set (SHUFD) and a real high-density underwater fish image data set (RHUFD). The proposed method has significant improvements over the state-of-the-art method (CUT) on SHUFD and RHUFD datasets, with the mean absolute error, mean square error, background region bias, foreground region bias and density map bias indicators improving by 3.44% and 6.47%, 11.43% and 4.41%, 23.91% and 29.48%, 4.43% and 10.33%, 8.3% and 13.14%, respectively.