List of Content
Back to Listing
| Title | Abstract | Action(s) |
|---|---|---|
| A Hybrid DL-Based Framework to Classify Malware using Mexican Hat Wavelet Function | Detecting and categorizing malware represents a substantial and demanding undertaking within the realm of information security and various other computer-related domains. Millions of malicious files are detected annually. The high volume is largely due to malware authors using mutations to evade detection, Malware variants are constantly evolving through the use of advanced obfuscation and packing methods, making detection and classification increasingly difficult. In order to efficiently examine and categorize a substantial volume of files, it becomes imperative to group them and ascertain their behavioral characteristics to classify them effectively. In recent, most malware classification techniques have been based on machine learning or deep learning models. These models work with the train and test. The models are trained with the features, for instance, opcode sequence, API calls, signature, etc. Recently, many deep learning techniques have been proposed for Alex Net Network, Resnet-50 Network, and Hybrid (AlexNet-Resnet-50). These models work well in terms of accuracy, Sensitivity, and so forth. However, these models are complex in nature and need high computational power. In order to adequately confront the difficulty presented by emerging malware variations, it becomes essential to employ alternative approaches, as conventional artificial intelligence and machine learning algorithms are no longer capable of identifying all intricate and constantly changing variants. A promising solution is deep learning, which differs from traditional machine learning. This study proposes a Mexican hat wavelet function that classifies malware variants through a hybrid deep learning model in this approach, malware samples undergo conversion into grayscale images before being fed into the DL system. Following the image acquisition section, the proposed method employs the convolution layers of the hybrid architecture to extract high-level malware features from the malware images with cloud-based architecture to decrease the computational intricacy, and neural network complexity to achieve higher accuracy. Upon subjecting the proposed method to testing using the MALIMG dataset, an accuracy of 99% was achieved. Similarly, when applied to the MALEVIS dataset, an accuracy of 97.12% was attained, outperforming the majority of machine learning-based methods employed for malware detection |
|
| A Hybrid DL-Based Framework to Classify Malware using Mexican Hat Wavelet Function | Detecting and categorizing malware represents a substantial and demanding undertaking within the realm of information security and various other computer-related domains. Millions of malicious files are detected annually. The high volume is largely due to malware authors using mutations to evade detection, Malware variants are constantly evolving through the use of advanced obfuscation and packing methods, making detection and classification increasingly difficult. In order to efficiently examine and categorize a substantial volume of files, it becomes imperative to group them and ascertain their behavioral characteristics to classify them effectively. In recent, most malware classification techniques have been based on machine learning or deep learning models. These models work with the train and test. The models are trained with the features, for instance, opcode sequence, API calls, signature, etc. Recently, many deep learning techniques have been proposed for Alex Net Network, Resnet-50 Network, and Hybrid (AlexNet-Resnet-50). These models work well in terms of accuracy, Sensitivity, and so forth. However, these models are complex in nature and need high computational power. In order to adequately confront the difficulty presented by emerging malware variations, it becomes essential to employ alternative approaches, as conventional artificial intelligence and machine learning algorithms are no longer capable of identifying all intricate and constantly changing variants. A promising solution is deep learning, which differs from traditional machine learning. This study proposes a Mexican hat wavelet function that classifies malware variants through a hybrid deep learning model in this approach, malware samples undergo conversion into grayscale images before being fed into the DL system. Following the image acquisition section, the proposed method employs the convolution layers of the hybrid architecture to extract high-level malware features from the malware images with cloud-based architecture to decrease the computational intricacy, and neural network complexity to achieve higher accuracy. Upon subjecting the proposed method to testing using the MALIMG dataset, an accuracy of 99% was achieved. Similarly, when applied to the MALEVIS dataset, an accuracy of 97.12% was attained, outperforming the majority of machine learning-based methods employed for malware detection |
|
| Efficient Geographical Routing Protocol using Beaconless approach in VANET | Vehicular ad hoc networks (VANETs) include the vehicles to communicate with each other and share the data with the central repositories. The intelligent transportation systems timely manage the traffic hazards and inform the nearby vehicles to ensure road safety. It is quite important to select the next relay node in VANET who can transmit the messages to next vehicles. For communication between vehicles, it is very important to select more accurate vehicles as next forwarder to avoid loops and increase the cost of the network. During the next forwarder node selection. It considers the long distance and large angle to choose the farthest node. The main problem is that it does not consider all possible realistic scenarios like the node at largest distance with greater angle. Also, it was not defining the case if those vehicles which have smaller distance to source node along the small angle with destination node. In this research, these parameters are defined and calculate their values by considering different scenarios. In proposed scenario, the network can achieve high throughput and packet delivery ratio, and reduce the delay in the network. The proposed protocol for vehicular network calculates the distance between node, angle of the nodes and traffic density of the road on the intersection point and set its priority according to the condition. The NS2 simulator is used to evaluate the performance of the proposed protocol. The proposed protocol achieved the better throughput, packet delivery ratio and reduce the delay as compared to BTA-GRP, IPN and IB. |
|
| Efficient Content Defined Chunking for Data Deduplication in IoT Assisted Cloud Computing |
|
|
| GESTURE GENERATION FROM URDU TEXT BASED ON DEEP LEARNING APPROACH |
|
|
| DESIGN AND OPTIMATIZATION OF NONLINEAR COMPONENT OF BLOCK CIPHER: APPLICATIONS TO MULTIMEDIA SECURITY |
|
|
| Modified Sir Model for Infectious Diseases Transmission with Lockdown and Vaccination Dynamics |
|
|
| AN IMPROVED ADDRESSING BASED ENERGY EFFICIENT ROUTING PROTOCOL FOR UNDERWATER WIRELESS SENSOR NETWORKS |
|
|
| AN IMPROVED CLASSIFICATION OF UNDERWATER SHIP-ENGINE AUDIOS USING SIAMESE NETWORK | Developing a reliable ship classification system using underwater acoustics is crucial due to limited labeled data, dynamic underwater conditions, and noise interference, reducing reliance on human sonar operators vulnerable to weather and fatigue. Improving underwater acoustic target classification requires addressing shortcomings in feature extraction, dataset availability, feature diversity, and classifier selection, but integrating multiple techniques must balance gains against increased costs, time, and system complexity. This study proposes a novel feature extraction technique that reduces the computational cost, complexity and increases the robustness of model. In this proposed technique, audios are segmented into chunks and spectrograms are calculated for them. The dataset is arranged in the form of triplets that are fed into the siamese network that are based on triplet loss, generates feature vectors. The goal of the siamese network is to learn an embedding space in which similar classes are grouped together and dissimilar classes are further separated. These extracted features may be fed into a classifier. Classifier will then classify the correct classes on the basis of given results. The model’s performance is evaluated on Shipears dataset. Furthermore, accuracy, precision, recall, f1-score and ROC curve are used to evaluate the performance of popular classifiers, k-NN, SVM, RF, DT. Overall accuracy of our model reaches 96.4167% which reduces the complexity. |
|
| SECURE DATA AGGREGATION AND DISSEMINATION USING BATCH KEYING IN INTERNET OF MEDICAL THINGS | The Internet of Medical Things (IoMT) is a new fastest growing technology that consist of wearable medical sensors to collect patient’s medical data and transmit it to the cloud repository for storage. It enables real time analysis of patient data and allow doctors to take preventive measures accordingly. The security of sensitive medical data is mandatory while transferring it via the Internet. The existing base scheme emphasizes on reducing the transmission costs and maintains the security of IoMT system. The value of the secret key is null at the initial phase while sending data from sensor node (SN) to head node (HN). Due to the null value, the risks of security attacks by intruders are increased. The Proposed Batch Key based Secure Data Aggregation (BK-SDA) scheme focus on minimizing the risks of security attacks and reducing the transmission cost by improving the algorithms. In Batch Key based Secure Data Aggregation at Head Node (BKSDA-HN) algorithm, it chooses a random number for secret key rather than null value at the initial phase. It also applies batch verification on received data to ensure its authenticity and then performs aggregation at HN. On the other Batch Key based Secure Data Extraction at Fog Server (BKSDE-FS) algorithm, the batch verification is also applied on received data before starting the process of data extraction. The BK-SDA scheme is implemented on NS 2.35 simulation tool to check the performance of proposed algorithms. In NS 2.35, the TCL files is used for nodes placement and C++ language to control the functionality of nodes and AWK files to extract results. The performance of BK-SDA is evaluated under three performance evaluation metrics like communication cost, computational cost, and energy consumption cost. The experimental result show that the performance of BK SDA scheme is better than other existing schemes to reduce communication cost and energy consumption cost but it consumes more computational cost as compare to others. The proposed BK-SDA scheme reduce the data transmission costs in terms of communication and energy consumption cost and improve the security algorithm to make the system more efficient and secure for data communication. |
|