Explore the vast range of titles available.

Accurate dermoscopic lesion segmentation is challenging because existing methods struggle to preserve fine-grained local structures while capturing long-range semantic context, leading to reduced robustness against unclear boundaries, imaging artifacts, and dataset shifts. We propose Hyper-Fusion Segmentation (H-Fusion SEG), a dual-branch framework that combines a boundary-sensitive U-Net encoder–decoder with a Segment Anything Model branch to jointly extract high-resolution local details and robust global semantics. A novel hyper-attention fusion module adaptively integrates these heterogeneous features and is optimized with boundary-aware objectives to enhance delineation and interpretability. On the ISIC-2016 dataset, H-Fusion SEG achieves IoU = 0.8775 and Dice = 0.9269 (+ 1.28% IoU, + 1.38% Dice over baselines), and on ISIC-2018, it achieves IoU = 0.9329 and Dice = 0.9629 (+ 8.69% IoU, + 6.69% Dice over baselines), with strong generalization to the HAM10000 dataset. These gains are particularly pronounced for complex lesions with indistinct or ambiguous boundaries. The proposed framework offers a flexible and generalizable solution for medical image segmentation, with promising potential for precise and reliable computer-aided diagnostic tools in dermatology. Code is available at: https://github.com/AnasHXH/Skin-DiseaseS-Segmentation .

The security of information is necessary for the success of any system. So, there is a need to have a robust mechanism to ensure the verification of any person before allowing him to access the stored data. So, for purposes of increasing the security level and privacy of users against attacks, cancelable biometrics can be utilized. The principal objective of cancelable biometrics is to generate new distorted biometric templates to be stored in biometric databases instead of the original ones. This paper presents effective methods based on different discrete transforms, such as Discrete Fourier Transform (DFT), Fractional Fourier Transform (FrFT), Discrete Cosine Transform (DCT), and Discrete Wavelet Transform (DWT), in addition to matrix rotation to generate cancelable biometric templates, in order to meet revocability and prevent the restoration of the original templates from the generated cancelable ones. Rotated versions of the images are generated in either spatial or transform domains and added together to eliminate the ability to recover the original biometric templates. The cancelability performance is evaluated and tested through extensive simulation results for all proposed methods on a different face and fingerprint datasets. Low Equal Error Rate (EER) values with high AROC values reflect the efficiency of the proposed methods, especially those dependent on DCT and DFrFT. Moreover, a comparative study is performed to evaluate the proposed method with all transformations to select the best one from the security perspective. Furthermore, a comparative analysis is carried out to test the performance of the proposed schemes with the existing schemes. The obtained outcomes reveal the efficiency of the proposed cancelable biometric schemes by introducing an average AROC of 0.998, EER of 0.0023, FAR of 0.008, and FRR of 0.003.

Millimetre wave (mmWave) communications, that is, 30 to 300 GHz, have intermittent short‐range transmissions, so the use of reconfigurable intelligent surface (RIS) seems to be a promising solution to extend its coverage. However, optimizing phase shifts (PSs) of both mmWave base station (BS) and RIS to maximize the received spectral efficiency at the intended receiver seems challenging due to massive antenna elements usage. In this paper, an online learning approach is proposed to address this problem, where it is considered a two‐phase multi‐armed bandit (MAB) game. In the first phase, the PS vector of the mmWave BS is adjusted, and based on it, the PS vector of the RIS is calibrated in the second phase and vice versa over the time horizon. The minimax optimal stochastic strategy (MOSS) MAB algorithm is utilized to implement the proposed two‐phase MAB approach efficiently. Furthermore, to relax the problem of estimating the channel state information (CSI) of both mmWave BS and RIS, codebook‐based PSs are considered. Finally, numerical analysis confirms the superior performance of the proposed scheme against the optimal performance under different scenarios.

Blockchain networks now support billions of dollars in daily transactions, making reliable and transparent fraud detection essential for maintaining user trust and financial stability. Yet, real‐world blockchain datasets are extremely imbalanced, with fraudulent activity representing less than 1% of all transactions. This imbalance causes conventional machine learning models to achieve deceptively high accuracy while still failing to detect a substantial portion of fraudulent events. To address this challenge, this study evaluates the performance and explainability of three models‐XGBoost, LightGBM, and Decision Tree‐on the Ethereum‐based fraud detection data, in which 58% of transactions are identified as fraud. The methodology combines vast feature engineering, k‐fold cross‐validation, and assorted resampling approaches, such as Synthetic Minority Oversampling Technique (SMOTE) and Adaptive Synthetic Sampling Nearest Neighbor (ADASYN), to revise the effect of class mismatch. Accuracy, AUC, recall, precision, F1‐Score, and Matthews Correlation Coefficient(MCC) are used to measure model performance, and SHapley Additive exPlanations (SHAP) is utilized to give global and local interpretability. Experimental results show that XGBoost combined with SMOTE or ADASYN yields the strongest performance, achieving a recall over 99%, an AUC of 1.000, and a substantially improved MCC compared to training on the raw imbalanced data. LightGBM presents a favourable precision‐recall balance, and Decision Trees demonstrate significant gains after resampling, despite their simplicity. SHAP analysis reveals that log‐transformed transaction amount, merchant‐based encoding, geographic encoding, and temporal features are the primary contributors to fraud risk. These results are important in highlighting two implications: (i) the importance of dealing with extreme class imbalance, rather than choosing increasingly sophisticated approaches, and (ii) the ability to be trusted to be explained is a requirement of responsible working in both financial and blockchain settings. The research offers a pragmatic, interpretable framework on blockchain fraud detection and future directions, including sophisticated hybrid sampling, collective learning, as well as cross‐chain generalization to enhance fraud detection in distributed systems. Research methodology pipeline for blockchain fraud detection.

The Vision Transformer (ViT) architecture has been remarkably successful in image restoration. For a while, Convolutional Neural Networks (CNN) predominated in most computer vision tasks. Now, both CNN and ViT are efficient approaches that demonstrate powerful capabilities to restore a better version of an image given in a low-quality format. In this study, the efficiency of ViT in image restoration is studied extensively. The ViT architectures are classified for every task of image restoration. Seven image restoration tasks are considered: Image Super-Resolution, Image Denoising, General Image Enhancement, JPEG Compression Artifact Reduction, Image Deblurring, Removing Adverse Weather Conditions, and Image Dehazing. The outcomes, the advantages, the limitations, and the possible areas for future research are detailed. Overall, it is noted that incorporating ViT in the new architectures for image restoration is becoming a rule. This is due to some advantages compared to CNN, such as better efficiency, especially when more data are fed to the network, robustness in feature extraction, and a better feature learning approach that sees better the variances and characteristics of the input. Nevertheless, some drawbacks exist, such as the need for more data to show the benefits of ViT over CNN, the increased computational cost due to the complexity of the self-attention block, a more challenging training process, and the lack of interpretability. These drawbacks represent the future research direction that should be targeted to increase the efficiency of ViT in the image restoration domain.

Modern web application development involves handling enormous amounts of sensitive and consequential data. Security is, therefore, a crucial component of developing web applications. A web application's security is concerned with safeguarding the data it processes. The web application framework must have safeguards to stop and find application vulnerabilities. Among all web application attacks, SQL injection and XSS attacks are common, which may lead to severe damage to Web application data or web functionalities. Currently, there are many solutions provided by various study for SQLi and XSS attack detection, but most of the work shown have used either SQL/XSS payload-based detection or HTTP request-based detection. Few solutions available can detect SQLi and XSS attacks, but these methods provide very high false positive rates, and the accuracy of these models can further be improved. We proposed a novel approach for securing web applications from both cross-site scripting attacks and SQL injection attacks using decoding and standardization of SQL and XSS payloads and HTTP requests and trained our model using hybrid deep learning networks in this paper. The proposed hybrid DL model combines the strengths of CNNs in extracting features from input data and LSTMs in capturing temporal dependencies in sequential data. The soundness of our approach lies in the use of deep learning techniques that can identify subtle patterns in the data that traditional machine learning-based methods might miss. We have created a testbed dataset of Normal and SQLi/XSS HTTP requests and evaluated the performance of our model on this dataset. We have also trained and evaluated the proposed model on the Benchmark dataset HTTP CSIC 2010 and another SQL/XSS payload dataset. The experimental findings show that our proposed approach effectively identifies these attacks with high accuracy and a low percentage of false positives. Additionally, our model performed better than traditional machine learning-based methods. This soundness approach can be applied to various network security applications such as intrusion detection systems and web application firewalls. Using our model, we achieved an accuracy of 99.84%, 99.23% and 99.77% on the SQL-XSS Payload dataset, Testbed dataset and HTTP CSIC 2010 dataset, respectively.

The Artificial Intelligence has evolved and is now associated with Deep Learning, driven by availability of vast amount of data and computing power. Traditionally, researchers have adopted a Model-Centric Approach, focusing on developing new algorithms and models to enhance performance without altering the underlying data. However, Andrew Ng, a prominent figure in the AI community, has recently emphasized on better (quality) data rather than better models, which has given birth to Data Centric Approach, also known as Data Oriented technique. The transition from model oriented to data oriented approach has rapidly gained momentum within the realm of deep learning. Despite its promise, the Data-Centric Approach faces several challenges, including (a) generating high-quality data, (b) ensuring data privacy, and (c) addressing biases to achieve fairness in datasets. Currently, there has been limited effort in preparing quality data. Our work aims to address this gap by focusing on the generation of high-quality data through methods such as data augmentation, multi-stage hashing to eliminate duplicate instances, to detect and correct noisy labels, using confident learning. The experiments on popular datasets, namely MNIST, Fashion MNIST, and CIFAR-10 were performed by utilizing ResNet-18 as the common framework followed by both Model Centric and Data Centric Approach. Comparative performance analysis revealed that the Data Centric Approach consistently outperformed the Model Centric Approach by a relative margin of at least 3%. This finding highlights the potential for further exploration and adoption of the Data-Centric Approach in various domains such as healthcare, finance, education, and entertainment, where the quality of data could significantly enhance the performance.

Nowadays, ransomware is considered one of the most critical cyber-malware categories. In recent years various malware detection and classification approaches have been proposed to analyze and explore malicious software precisely. Malware originators implement innovative techniques to bypass existing security solutions. This paper introduces an efficient End-to-End Ransomware Detection System (E2E-RDS) that comprehensively utilizes existing Ransomware Detection (RD) approaches. E2E-RDS considers reverse engineering the ransomware code to parse its features and extract the important ones for prediction purposes, as in the case of static-based RD. Moreover, E2E-RDS can keep the ransomware in its executable format, convert it to an image, and then analyze it, as in the case of vision-based RD. In the static-based RD approach, the extracted features are forwarded to eight various ML models to test their detection efficiency. In the vision-based RD approach, the binary executable files of the benign and ransomware apps are converted into a 2D visual (color and gray) images. Then, these images are forwarded to 19 different Convolutional Neural Network (CNN) models while exploiting the substantial advantages of Fine-Tuning (FT) and Transfer Learning (TL) processes to differentiate ransomware apps from benign apps. The main benefit of the vision-based approach is that it can efficiently detect and identify ransomware with high accuracy without using data augmentation or complicated feature extraction processes. Extensive simulations and performance analyses using various evaluation metrics for the proposed E2E-RDS were investigated using a newly collected balanced dataset that composes 500 benign and 500 ransomware apps. The obtained outcomes demonstrate that the static-based RD approach using the AB (Ada Boost) model achieved high classification accuracy compared to other examined ML models, which reached 97%. While the vision-based RD approach achieved high classification accuracy, reaching 99.5% for the FT ResNet50 CNN model. It is declared that the vision-based RD approach is more cost-effective, powerful, and efficient in detecting ransomware than the static-based RD approach by avoiding feature engineering processes. Overall, E2E-RDS is a versatile solution for end-to-end ransomware detection that has proven its high efficiency from computational and accuracy perspectives, making it a promising solution for real-time ransomware detection in various systems.

Vehicle identification systems are vital components that enable many aspects of contemporary life, such as safety, trade, transit, and law enforcement. They improve community and individual well-being by increasing vehicle management, security, and transparency. These tasks entail locating and extracting license plates from images or video frames using computer vision and machine learning techniques, followed by recognizing the letters or digits on the plates. This paper proposes a new license plate detection and recognition method based on the deep learning YOLO v8 method, image processing techniques, and the OCR technique for text recognition. For this, the first step was the dataset creation, when gathering 270 images from the internet. Afterward, CVAT (Computer Vision Annotation Tool) was used to annotate the dataset, which is an open-source software platform made to make computer vision tasks easier to annotate and label images and videos. Subsequently, the newly released Yolo version, the Yolo v8, has been employed to detect the number plate area in the input image. Subsequently, after extracting the plate the k-means clustering algorithm, the thresholding techniques, and the opening morphological operation were used to enhance the image and make the characters in the license plate clearer before using OCR. The next step in this process is using the OCR technique to extract the characters. Eventually, a text file containing only the character reflecting the vehicle's country is generated. To ameliorate the efficiency of the proposed approach, several metrics were employed, namely precision, recall, F1-Score, and CLA. In addition, a comparison of the proposed method with existing techniques in the literature has been given. The suggested method obtained convincing results in both detection as well as recognition by obtaining an accuracy of 99% in detection and 98% in character recognition.

This paper offers a comprehensive analysis model for android malware. The model presents the essential factors affecting the analysis results of android malware that are vision-based. Current android malware analysis and solutions might consider one or some of these factors while building their malware predictive systems. However, this paper comprehensively highlights these factors and their impacts through a deep empirical study. The study comprises 22 CNN (Convolutional Neural Network) algorithms, 21 of them are well-known, and one proposed algorithm. Additionally, several types of files are considered before converting them to images, and two benchmark android malware datasets are utilized. Finally, comprehensive evaluation metrics are measured to assess the produced predictive models from the security and complexity perspectives. Consequently, guiding researchers and developers to plan and build efficient malware analysis systems that meet their requirements and resources. The results reveal that some factors might significantly impact the performance of the malware analysis solution. For example, from a security perspective, the accuracy, F1-score, precision, and recall are improved by 131.29%, 236.44%, 192%, and 131.29%, respectively, when changing one factor and fixing all other factors under study. Similar results are observed in the case of complexity assessment, including testing time, CPU usage, storage size, and pre-processing speed, proving the importance of the proposed android malware analysis model.