Distributed Denial-of-Service (DDoS) attacks are increasing as the demand for Internet connectivity massively grows in recent years. Conventional shallow machine learning-based techniques for DDoS attack classification tend to be ineffective when the volume and features of network traffic, potentially carry malicious DDoS payloads, increase exponentially as they cannot extract high importance features automatically. To address this concern, we propose a hybrid approach named AE-MLP that combines two deep learning-based models for effective DDoS attack detection and classification. The Autoencoder (AE) part of our proposed model provides an effective feature extraction that finds the most relevant feature sets automatically without human intervention (e.g., knowledge of cybersecurity professionals). The Multilayer Perceptron Network (MLP) part of our proposed model uses the compressed and reduced feature sets produced by the AE as inputs and classifies the attacks into different DDoS attack types to overcome the performance overhead and bias associated with processing large feature sets with noise (i.e., unnecessary feature values). Our experimental results, obtained through comprehensive and extensive experiments on different aspects of performance on the CICDDoS2019 dataset, demonstrate both a very high and robust accuracy rate and F1-score that exceed 98% which also outperformed the performance of many similar methods. This shows that our proposed model can be used as an effective DDoS defense tool against the growing number of DDoS attacks.

Network anomaly detection plays a crucial role as it provides an effective mechanism to block or stop cyberattacks. With the recent advancement of Artificial Intelligence (AI), there has been a number of Autoencoder (AE) based deep learning approaches for network anomaly detection to improve our posture towards network security. The performance of existing state-of-the-art AE models used for network anomaly detection varies without offering a holistic approach to understand the critical impacts of the core set of important performance indicators of AE models and the detection accuracy. In this study, we propose a novel 5-layer autoencoder (AE)-based model better suited for network anomaly detection tasks. Our proposal is based on the results we obtained through an extensive and rigorous investigation of several performance indicators involved in an AE model. In our proposed model, we use a new data preprocessing methodology that transforms and removes the most affected outliers from the input samples to reduce model bias caused by data imbalance across different data types in the feature set. Our proposed model utilizes the most effective reconstruction error function which plays an essential role for the model to decide whether a network traffic sample is normal or anomalous. These sets of innovative approaches and the optimal model architecture allow our model to be better equipped for feature learning and dimension reduction thus producing better detection accuracy as well as f1-score. We evaluated our proposed model on the NSL-KDD dataset which outperformed other similar methods by achieving the highest accuracy and f1-score at 90.61% and 92.26% respectively in detection.

This paper proposes a novel identity management framework for Internet of Things (IoT) and cloud computing-based personalized healthcare systems. The proposed framework uses multimodal encrypted biometric traits to perform authentication. It employs a combination of centralized and federated identity access techniques along with biometric based continuous authentication. The framework uses a fusion of electrocardiogram (ECG) and photoplethysmogram (PPG) signals when performing authentication. In addition to relying on the unique identification characteristics of the users’ biometric traits, the security of the framework is empowered by the use of Homomorphic Encryption (HE). The use of HE allows patients’ data to stay encrypted when being processed or analyzed in the cloud. Thus, providing not only a fast and reliable authentication mechanism, but also closing the door to many traditional security attacks. The framework’s performance was evaluated and validated using a machine learning (ML) model that tested the framework using a dataset of 25 users in seating positions. Compared to using just ECG or PPG signals, the results of using the proposed fused-based biometric framework showed that it was successful in identifying and authenticating all 25 users with 100% accuracy. Hence, offering some significant improvements to the overall security and privacy of personalized healthcare systems.

No abstract

During the recent COVID-19 outbreak, educational institutions have transitioned to online teaching for all students for most of the programs. Due to lack of in-person interactions and monitoring, assessments in online courses may be more susceptible to contract cheating, collusion, fabrication and other types of academic misconduct than the assessments in face-to-face courses. This situation has raised several research questions that need immediate attention, such as what are the best possible options for online assessments and how to administer online assessments so that academic integrity could be preserved. The authors have conducted a scoping study and carried out an extensive literature review on i) different types of assessments that are suitable for online courses, ii) strategies for ensuring academic integrity, and iii) methods, tools and technologies available for preventing academic misconduct in online assessments. It is evident from the literature review that there are a range of options available for designing assessment tasks to detect and prevent violations of academic integrity. However, no single method or design is enough to eliminate all sorts of academic integrity violations. After thorough research and analysis of existing literature, the authors have provided a comprehensive set of recommendations that could be adopted for ensuring academic integrity in online assessments.

Abstract-This paper presents a novel mechanism for dynamically adapting the quality of congestion controlled Voice Over IP (VoIP) applications on the internet in real time. The system uses our proposed variable bit rate speech codec called Speex, which can dynamically adjust the encoding bit rate (and hence the speech quality) based on both the feedback information about the network congestion and the instantaneous speech properties. Our extensive NS2 simulation results prove that the proposed system indeed provides highest quality speech while maximising the bandwidth utilisation and reducing the network congestion.

No abstract

Smart cities use the Internet of Things (IoT) devices such as connected sensors, lights, and meters to collect and analyze data to improve infrastructure, public utilities, and services. However, the true potential of smart cities cannot be leveraged without addressing many security concerns. In particular, there is a significant challenge for provisioning a reliable access control solution to share IoT data among various users across organizations. We present a novel entitlement-based blockchain-enabled access control architecture that can be used for smart cities (and for any ap-plication domains that require large-scale IoT deployments). Our proposed entitlement-based access control model is flexible as it facilitates a resource owner to safely delegate access rights to any entities beyond the trust boundary of an organization. The detailed design and implementation on Ethereum blockchain along with a qualitative evaluation of the security and access control aspects of the proposed scheme are presented in the paper. The experimental results from private Ethereum test networks demonstrate that our proposal can be easily implemented with low latency. This validates that our proposal is applicable to use in the real world IoT environments.