Department of Computer Science and Information Systems

Permanent URI for this collectionhttp://localhost:4000/handle/123456789/1928

Browse

Filters

2022 - 20243

Settings

Author: search.filters.author.Dua, AmitSubject: search.filters.subject.Deep learning

Search Results

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    ConvXSS: A deep learning-based smart ICT framework against code injection attacks for HTML5 web applications in sustainable smart city infrastructure
    (Elsevier, 2022-05) Dua, Amit; Gupta, Shashank
    In this paper we propose ConvXSS, a novel deep learning approach for the detection of XSS and code injection attacks, followed by context-based sanitization of the malicious code if the model detects any malicious code in the application. Firstly, we briefly discuss XSS and code injection attacks that might pose threat to sustainable smart cities. Along with this, we discuss various approaches proposed previously for the detection and alleviation of these attacks followed by their respective limitations. Then we propose our deep learning model adopting whose novelty is based on the approach followed for Data Pre-Processing. Then we finally propose Context-based Sanitization to replace the malicious part of the code with sanitized code. Numerical experiments conducted on various datasets have shown various results out of which the best model has an accuracy of 99.42%, a precision of 99.81% and a recall of 99.35%. When compared with other state of the art techniques in this domain, our approach shows at par or in the best case, better results in terms of detection speed and accuracy of CSS attacks.
  • No Thumbnail Available
    Item
    Deep Learning Approach for SDN-Enabled Intrusion Detection System in IoT Networks
    (MDPI, 2023-01) Dua, Amit
    Owing to the prevalence of the Internet of things (IoT) devices connected to the Internet, the number of IoT-based attacks has been growing yearly. The existing solutions may not effectively mitigate IoT attacks. In particular, the advanced network-based attack detection solutions using traditional Intrusion detection systems are challenging when the network environment supports traditional as well as IoT protocols and uses a centralized network architecture such as a software defined network (SDN). In this paper, we propose a long short-term memory (LSTM) based approach to detect network attacks using SDN supported intrusion detection system in IoT networks. We present an extensive performance evaluation of the machine learning (ML) and deep learning (DL) model in two SDNIoT-focused datasets. We also propose an LSTM-based architecture for the effective multiclass classification of network attacks in IoT networks. Our evaluation of the proposed model shows that our model effectively identifies the attacks and classifies the attack types with an accuracy of 0.971. In addition, various visualization methods are shown to understand the dataset’s characteristics and visualize the embedding features.
  • No Thumbnail Available
    Item
    DEEP-CARDIO: Recommendation System for Cardiovascular Disease Prediction Using IoT Network
    (IEEE, 2024-05) Dua, Amit
    The Internet of Things (IoTs)-based remote healthcare applications provide fast and preventative medical services to the patients at risk. However, predicting heart disease is a complex task, and diagnosis results are rarely accurate. To address this issue, a novel Recommendation System for Cardiovascular Disease (CVD) Prediction Using IoT Network (DEEP-CARDIO) has been proposed for providing prior diagnosis, treatment, and dietary recommendations for cardiac diseases. Initially, the physiological data are collected from the patients remotely by using the four biosensors, such as ECG sensor, pressure sensor, pulse sensor, and glucose sensor. An Arduino controller receives the collected data from the IoT sensors to predict and diagnose the disease. A CVD prediction model is implemented by using bidirectional-gated recurrent unit (BiGRU) attention model, which diagnoses the CVD and classifies into five available cardiovascular classes. The recommendation system provides physical and dietary recommendations to cardiac patients based on the classified data, via user mobile application. The performance of the DEEP-CARDIO is validated by Cloud Simulator (CloudSim) using the real-time Framingham’s and Statlog heart disease dataset. The proposed DEEP CARDIO method achieves an overall accuracy of 99.90%, whereas the MABC-SVM, HCBDA, and MLbPM methods achieve 86.91%, 88.65%, and 93.63%, respectively.