Search

Cross-Site Scripting (XSS) remains a significant threat to web application security, exploiting vulnerabilities to hijack user sessions and steal sensitive data. Traditional detection methods often fail to keep pace with the evolving sophistication of cyber threats. This paper introduces a novel hybrid ensemble learning framework that leverages a combination of advanced machine learning algorithms—Logistic Regression (LR), Support Vector Machines (SVM), eXtreme Gradient Boosting (XGBoost), Categorical Boosting (CatBoost), and Deep Neural Networks (DNN). Utilizing the XSS-Attacks-2021 dataset, which comprises 460 instances across various real-world traffic-related scenarios, this framework significantly enhances XSS attack detection. Our approach, which includes rigorous feature engineering and model tuning, not only optimizes accuracy but also effectively minimizes false positives (FP) (0.13%) and false negatives (FN) (0.19%). This comprehensive methodology has been rigorously validated, achieving an unprecedented accuracy of 99.87%. The proposed system is scalable and efficient, capable of adapting to the increasing number of web applications and user demands without a decline in performance. It demonstrates exceptional real-time capabilities, with the ability to detect XSS attacks dynamically, maintaining high accuracy and low latency even under significant loads. Furthermore, despite the computational complexity introduced by the hybrid ensemble approach, strategic use of parallel processing and algorithm tuning ensures that the system remains scalable and performs robustly in real-time applications. Designed for easy integration with existing web security systems, our framework supports adaptable Application Programming Interfaces (APIs) and a modular design, facilitating seamless augmentation of current defenses. This innovation represents a significant advancement in cybersecurity, offering a scalable and effective solution for securing modern web applications against evolving threats. [ABSTRACT FROM AUTHOR]

Neuroimaging has emerged over the last few decades as a crucial tool in diagnosing Alzheimer's disease (AD). Mild cognitive impairment (MCI) is a condition that falls between the spectrum of normal cognitive function and AD. However, previous studies have mainly used handcrafted features to classify MCI, AD, and normal control (NC) individuals. This paper focuses on using gray matter (GM) scans obtained through magnetic resonance imaging (MRI) for the diagnosis of individuals with MCI, AD, and NC. To improve classification performance, we developed two transfer learning strategies with data augmentation (i.e. shear range, rotation, zoom range, channel shift). The first approach is a deep Siamese network (DSN), and the second approach involves using a cross-domain strategy with customized VGG-16. We performed experiments on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset to evaluate the performance of our proposed models. Our experimental results demonstrate superior performance in classifying the three binary classification tasks: NC vs. AD, NC vs. MCI, and MCI vs. AD. Specifically, we achieved a classification accuracy of 97.68%, 94.25%, and 92.18% for the three cases, respectively. Our study proposes two transfer learning strategies with data augmentation to accurately diagnose MCI, AD, and normal control individuals using GM scans. Our findings provide promising results for future research and clinical applications in the early detection and diagnosis of AD. [ABSTRACT FROM AUTHOR]

Algorithms for steganography are methods of hiding data transfers in media files. Several machine learning architectures have been presented recently to improve stego image identification performance by using spatial information, and these methods have made it feasible to handle a wide range of problems associated with image analysis. Images with little information or low payload are used by information embedding methods, but the goal of all contemporary research is to employ high-payload images for classification. To address the need for both low- and high-payload images, this work provides a machine-learning approach to steganography image classification that uses Curvelet transformation to efficiently extract characteristics from both type of images. SupportVectorMachine (SVM), a commonplace classification technique, has been employed to determinewhether the image is a stego or cover. TheWavelet ObtainedWeights (WOW), Spatial UniversalWavelet Relative Distortion (S-UNIWARD), Highly Undetectable Steganography (HUGO), and Minimizing the Power of Optimal Detector (MiPOD) steganography techniques are used in a variety of experimental scenarios to evaluate the performance of the proposedmethod. UsingWOWat several payloads, the proposed approach proves its classification accuracy of 98.60%. It exhibits its superiority over SOTA methods. [ABSTRACT FROM AUTHOR]

Securing digital image data is a key concern in today’s information-driven society. Effective encryption techniques are required to protect sensitive image data, with the Substitution-box (S-box) often playing a pivotal role in many symmetric encryption systems. This study introduces an innovative approach to creating S-boxes for encryption algorithms. The proposed S-boxes are tested for validity and non-linearity by incorporating them into an image encryption scheme. The nonlinearity measure of the proposed S-boxes is 112. These qualities significantly enhance its resistance to common cryptographic attacks, ensuring high image data security. Furthermore, to assess the robustness of the S-boxes, an encryption system has also been proposed and the proposed S-boxes have been integrated into the designed encryption system. To validate the effectiveness of the proposed encryption system, a comprehensive security analysis including brute force attack and histogram analysis has been performed. In addition, to determine the level of security during the transmission and storage of digital content, the encryption system’s Number of Pixel Change Rate (NPCR), and Unified Averaged Changed Intensity (UACI) are calculated. The results indicate a 99.71% NPCR and 33.51% UACI. These results demonstrate that the proposed S-boxes offer a significant level of security for digital content throughout its transmission and storage. [ABSTRACT FROM AUTHOR]

Due to the inherent insecure nature of the Internet, it is crucial to ensure the secure transmission of image data over this network. Additionally, given the limitations of computers, it becomes even more important to employ efficient and fast image encryption techniques. While 1D chaotic maps offer a practical approach to real-time image encryption, their limited flexibility and increased vulnerability restrict their practical application. In this research, we have utilized a 3D Hindmarsh-Rose model to construct a secure cryptosystem. The randomness of the chaotic map is assessed through standard analysis. The proposed system enhances security by incorporating an increased number of system parameters and a wide range of chaotic parameters, as well as ensuring a uniform distribution of chaotic signals across the entire value space. Additionally, a fast image encryption technique utilizing the new chaotic system is proposed. The novelty of the approach is confirmed through time complexity analysis. To further strengthen the resistance against cryptanalysis attacks and differential attacks, the SHA-256 algorithm is employed for secure key generation. Experimental results through a number of parameters demonstrate the strong cryptographic performance of the proposed image encryption approach, highlighting its exceptional suitability for secure communication. Moreover, the security of the proposed scheme has been compared with stateof-the-art image encryption schemes, and all comparison metrics indicate the superior performance of the proposed scheme. [ABSTRACT FROM AUTHOR]

Independent human living systems require smart, intelligent, and sustainable online monitoring so that an individual can be assisted timely. Apart from ambient assisted living, the task of monitoring human activities plays an important role in different fields including virtual reality, surveillance security, and human interaction with robots. Such systems have been developed in the past with the use of various wearable inertial sensors and depth cameras to capture the human actions. In this paper, we propose multiple methods such as random occupancy pattern, spatio temporal cloud, waypoint trajectory, Hilbert transform, Walsh Hadamard transform and bone pair descriptors to extract optimal features corresponding to different human actions. These features sets are then normalized using min-max normalization and optimized using the Fuzzy optimization method. Finally, the Masi entropy classifier is applied for action recognition and classification. Experiments have been performed on three challenging datasets, namely, UTDMHAD, 50 Salad, and CMU-MMAC. During experimental evaluation, the proposed novel approach of recognizing human actions has achieved an accuracy rate of 90.1% with UTD-MHAD dataset, 90.6% with 50 Salad dataset, and 89.5% with CMU-MMAC dataset. Hence experimental results validated the proposed system. [ABSTRACT FROM AUTHOR]

Virtual reality is an emerging field in the whole world. The problem faced by people today is that they are more indulged in indoor technology rather than outdoor activities. Hence, the proposed system introduces a fitness solution connecting virtual reality with a gaming interface so that an individual can play first-person games. The system proposed in this paper is an efficient and cost-effective solution that can entertain people along with playing outdoor games such as badminton and cricket while sitting in the room. To track the human movement, sensors Micro Processor Unit (MPU6050) are used that are connected with Bluetoothmodules andArduino responsible for sending the sensor data to the game. Further, the sensor data is sent to a machine learning model, which detects the game played by the user. The detected game will be operated on human gestures. A publicly available dataset named IM-Sporting Behaviors is initially used, which utilizes triaxial accelerometers attached to the subject's wrist, knee, and below neck regions to capture important aspects of human motion. The main objective is that the person is enjoying while playing the game and simultaneously is engaged in some kind of sporting activity. The proposed system uses artificial neural networks classifier giving an accuracy of 88.9%. The proposed system should apply to many systems such as construction, education, offices and the educational sector. Extensive experimentation proved the validity of the proposed system. [ABSTRACT FROM AUTHOR]

Latest advancements in vision technology offer an evident impact on multi-object recognition and scene understanding. Such sceneunderstanding task is a demanding part of several technologies, like augmented reality-based scene integration, robotic navigation, autonomous driving, and tourist guide. Incorporating visual information in contextually unified segments, convolution neural networks-based approaches will significantly mitigate the clutter, which is usual in classical frameworks during scene understanding. In this paper, we propose a convolutional neural network (CNN) based segmentation method for the recognition of multiple objects in an image. Initially, after acquisition and preprocessing, the image is segmented by using CNN. Then, CNN features are extracted from these segmented objects, and discrete cosine transform (DCT) and discrete wavelet transform (DWT) features are computed. After the extraction of CNN features and computation of classical machine learning features, fusion is performed using a fusion technique. Then, to select theminimal set of features, genetic algorithm-based feature selection is used. In order to recognize and understand the multi-objects in the scene, a neuro-fuzzy approach is applied. Once objects in the scene are recognized, the relationship between these objects is examined by employing the object-to-object relation approach. Finally, a decision tree is incorporated to assign the relevant labels to the scenes based on recognized objects in the image. The experimental results over complex scene datasets including SUN Red Green Blue-Depth (RGB-D) and Cityscapes' demonstrated a remarkable performance. [ABSTRACT FROM AUTHOR]

E-learning approaches are one of the most important learning platforms for the learner through electronic equipment. Such study techniques are useful for other groups of learners such as the crowd, pedestrian, sports, transports, communication, emergency services, management systems and education sectors. E-learning is still a challenging domain for researchers and developers to find new trends and advanced tools and methods. Many of them are currently working on this domain to fulfill the requirements of industry and the environment. In this paper, we proposed a method for pedestrian behavior mining of aerial data, using deep flow feature, graph mining technique, and convocational neural network. For input data, the state-of-the-art crowd activity University of Minnesota (UMN) dataset is adopted, which contains the aerial indoor and outdoor view of the pedestrian, for simplification of extra information and computational cost reduction the pre-processing is applied. Deep flow features are extracted to find more accurate information. Furthermore, to deal with repetition in features data and features mining the graph mining algorithm is applied, while Convolution Neural Network (CNN) is applied for pedestrian behavior mining. The proposed method shows 84.50% of mean accuracy and a 15.50% of error rate. Therefore, the achieved results show more accuracy as compared to state-ofthe-art classification algorithms such as decision tree, artificial neural network (ANN). [ABSTRACT FROM AUTHOR]

Human object interaction (HOI) recognition plays an important role in the designing of surveillance and monitoring systems for healthcare, sports, education, and public areas. It involves localizing the human and object targets and then identifying the interactions between them. However, it is a challenging task that highly depends on the extraction of robust and distinctive features from the targets and the use of fast and efficient classifiers. Hence, the proposed system offers an automated body-parts-based solution for HOI recognition. This system uses RGB (red, green, blue) images as input and segments the desired parts of the images through a segmentation technique based on the watershed algorithm. Furthermore, a convex hullbased approach for extracting key body parts has also been introduced. After identifying the key body parts, two types of features are extracted. Moreover, the entire feature vector is reduced using a dimensionality reduction technique called t-SNE (t-distributed stochastic neighbor embedding). Finally, a multinomial logistic regression classifier is utilized for identifying class labels. A large publicly available dataset, MPII (Max Planck Institute Informatics) Human Pose, has been used for system evaluation. The results prove the validity of the proposed system as it achieved 87.5% class recognition accuracy. [ABSTRACT FROM AUTHOR]

Over the last decade, there is a surge of attention in establishing ambient assisted living (AAL) solutions to assist individuals live independently. With a social and economic perspective, the demographic shift toward an elderly population has brought new challenges to today's society. AAL can offer a variety of solutions for increasing people's quality of life, allowing them to live healthier and more independently for longer. In this paper, we have proposed a novel AAL solution using a hybrid bidirectional long-term and short-term memory networks (BiLSTM) and convolutional neural network (CNN) classifier. We first pre-processed the signal data, then used timefrequency features such as signal energy, signal variance, signal frequency, empirical mode, and empirical mode decomposition. The convolutional neural network-bidirectional long-termand short-termmemory (CNN-biLSTM) classifier with dimensional reduction isomap algorithm was then used to select ideal features. We assessed the performance of our proposed system on the publicly accessible human gait database (HuGaDB) benchmark dataset and achieved an accuracy rates of 93.95 percent, respectively. Experiments reveal that hybrid method gives more accuracy than single classifier in AAL model. The suggested system can assists persons with impairments, assisting carers and medical personnel. [ABSTRACT FROM AUTHOR]

In this research work, an efficient sign language recognition tool for e-learning has been proposed with a new type of feature set based on angle and lines. This feature set has the ability to increase the overall performance of machine learning algorithms in an efficient way. The hand gesture recognition based on these features has been implemented for usage in real-time. The feature set used hand landmarks, which were generated using media-pipe (MediaPipe) and open computer vision (openCV) on each frame of the incoming video. The overall algorithm has been tested on two well-known ASL-alphabet (American Sign Language) and ISL-HS (Irish Sign Language) sign language datasets. Different machine learning classifiers including random forest, decision tree, and naïve Bayesian have been used to classify hand gestures using this unique feature set and their respective results have been compared. Since the random forest classifier performed better, it has been selected as the base classifier for the proposed system. It showed 96.7% accuracy with ISL-HS and 93.7% accuracy with ASL-alphabet dataset using the extracted features. [ABSTRACT FROM AUTHOR]

Human Activity Recognition (HAR) plays an important role in life care and health monitoring since it involves examining various activities of patients at homes, hospitals, or offices. Hence, the proposed system integrates Human-Human Interaction (HHI) and Human-Object Interaction (HOI) recognition to provide in-depth monitoring of the daily routine of patients. We propose a robust system comprising both RGB (red, green, blue) and depth information. In particular, humans in HHI datasets are segmented via connected components analysis and skin detection while the human and object in HOI datasets are segmented via saliency map. To track the movement of humans, we proposed orientation and thermal features. A codebook is generated using Linde-Buzo-Gray (LBG) algorithm for vector quantization. Then, the quantized vectors generated from image sequences of HOI are given to Artificial Neural Network (ANN) while the quantized vectors generated from image sequences of HHI are given to K-ary tree hashing for classification. There are two publicly available datasets used for experimentation on HHI recognition: Stony Brook University (SBU) Kinect interaction and the University of Lincoln's (UoL) 3D social activity dataset. Furthermore, two publicly available datasets are used for experimentation on HOI recognition: Nanyang Technological University (NTU) RGB-D and Sun Yat-Sen University (SYSU) 3D HOI datasets. The results proved the validity of the proposed system. [ABSTRACT FROM AUTHOR]

In the new era of technology, daily human activities are becoming more challenging in terms of monitoring complex scenes and backgrounds. To understand the scenes and activities from human life logs, human-object interaction (HOI) is important in terms of visual relationship detection and human pose estimation. Activities understanding and interaction recognition between human and object along with the pose estimation and interaction modeling have been explained. Some existing algorithms and feature extraction procedures are complicated including accurate detection of rare human postures, occluded regions, and unsatisfactory detection of objects, especially small-sized objects. The existing HOI detection techniques are instance-centric (object-based) where interaction is predicted between all the pairs. Such estimation depends on appearance features and spatial information. Therefore, we propose a novel approach to demonstrate that the appearance features alone are not sufficient to predict the HOI. Furthermore, we detect the human body parts by using the Gaussian Matric Model (GMM) followed by object detection using YOLO. We predict the interaction points which directly classify the interaction and pair them with densely predicted HOI vectors by using the interaction algorithm. The interactions are linked with the human and object to predict the actions. The experiments have been performed on two benchmark HOI datasets demonstrating the proposed approach. [ABSTRACT FROM AUTHOR]

With the advancement of computer vision techniques in surveillance systems, the need for more proficient, intelligent, and sustainable facial expressions and age recognition is necessary. The main purpose of this study is to develop accurate facial expressions and an age recognition system that is capable of error-free recognition of human expression and age in both indoor and outdoor environments. The proposed system first takes an input image pre-process it and then detects faces in the entire image. After that landmarks localization helps in the formation of synthetic face mask prediction. A novel set of features are extracted and passed to a classifier for the accurate classification of expressions and age group. The proposed system is tested over two benchmark datasets, namely, the Gallagher collection person dataset and the Images of Groups dataset. The system achieved remarkable results over these benchmark datasets about recognition accuracy and computational time. The proposed system would also be applicable in different consumer application domains such as online business negotiations, consumer behavior analysis, E-learning environments, and emotion robotics. [ABSTRACT FROM AUTHOR]