Attacks on cloud computing (CC) services and infrastructure have raised concerns about the efficacy of data protection mechanisms in this environment. The framework developed in this study (CCAID: cloud computing, attack, and intrusion detection) aims to improve the performance of intrusion detection systems (IDS) operating in CC environments. It deploys a proposed new hybrid ensemble feature selection (FS) method. The ensemble includes FS algorithms of three different types (filter, wrapper, and embedded algorithms). The selected features used to train the ML (machine learning) model of the intrusion detection component comprised a binary detection engine for the identification of malicious/attack packets and a multiclassification detection engine for the identification of the type of attack. Both detection engines deploy ensemble classifiers. Experiments were carried out using the NSL KDD dataset. The binary model achieved a classification accuracy of 99.55% with a very low false alarm rate of 0.45%. The classification accuracy of the multiclassification model was also high (98.92%). These results compare very favourably with the results reported in the literature and indicate the feasibility of the framework implementation.

Denial-of-service (DoS) attacks pose a significant threat to wireless sensor networks (WSNs) and are an impediment to their mass deployment. Current research has identified trust models as a plausible defense against DoS attacks. However, most of the proposed solutions focus only on one or two specific DoS attack scenarios and provide very limited guidance to a WSN with regard to important practical aspects, such as setting up threshold configurations and weight allocation schemes. This study conducts a comparative analysis of relevant work to build a foundation for the development of robust trust models that can counter a range of different types of DoS attacks in WSNs. In particular, this study examines the required trust evidence, the methods for extracting trust evidence, and the trust evaluation techniques for developing effective trust models. This study identifies the challenges in the implementation of trust models, such as the need to determine feasible threshold limits and trust metric weightings and the need to manage the loss of trust information. In addition, this study explores link quality and node authentication as factors affecting trust evaluation and the integration of trust models with network routing protocols.

We propose a new authenticated key agreement scheme based on Blom’s scheme, but using multiple master keys and public keys in permutations to compute the private keys in each node. The computations are over a small prime field, and by storing them in a random order in the node, the private-public-master-key associations (PPMka) of the private keys are lost. If a node is captured, the PPMka of the private keys cannot be determined with certainty, making it difficult to begin to attack the scheme. We obtained analytical results to show that, using suitable keying parameters, the probability of discovering the correct PPMka can be made so small, that a very powerful adversary needs to capture the entire network of tens of thousands of nodes or expend an infeasible amount of effort to try all of the possible solutions. We verified our results using computer-simulated attacks on the scheme. The unknown PPMka enables our scheme to break free from the capture threshold of the original Blom’s scheme, so that it can be used in large networks of low-resource devices, such as sensor nodes.

Mobile devices (MDs) are used by mobile cloud computing (MCC) customers and by other users because of their portability, robust connectivity, and ability to house and operate third-party applications (apps). However, the apps installed on an MD may pose data security risks to the MD owner and to other MCC users, especially when the requested permissions include access to sensitive data (e.g., user’s location and contacts). Calculating the risk score of an app or quantifying its potential harmfulness based on user input or on data gathered while the app is actually running may not provide reliable and sufficiently accurate results to avoid harmful consequences. This study develops and evaluates a risk assessment framework for Android-based MDs that does not depend on user input or on actual app behavior. Rather, an app risk evaluator assigns a risk category to each resident app based on the app’s classification (benign or malicious) and the app’s risk score. The app classifier (a trained machine learning model) evaluates the permissions and intents requested by the app. The app risk score is calculated by applying a probabilistic function based on the app’s use of a set of selected dangerous permissions. The results from testing of the framework on an MD with real-life resident apps indicated that the proposed security solution was effective and feasible.

Wireless sensor networks (WSNs), including Software-Defined Wireless Sensors, are particularly vulnerable to Denial-of-Service (DoS) attacks. Trust models are widely acknowledged as an effective strategy to mitigate the threat of successful DoS attacks in WSNs. However, existing trust models commonly rely on threshold configurations that are based on the network administrator’s experience and leave the challenging task of weight allocation for various trust metrics to network users. This limits the widespread application of trust models as a WSN defence mechanism. To address that issue, this study proposes and theoretically analyses an Adaptive, Threshold-Free, and Automatically Weighted Trust Model (ATAW-TM) for SDWSNs. The model architecture is aligned with the layered centralized management architecture of SDWSNs, which makes it flexible and enhances its responsiveness. The proposed model does not require manual threshold configuration and weight allocation and allows for rapid trust system recovery. It has significant advantages compared to existing trust models and is potentially more feasible to implement on a large scale.

Mobile cloud computing (MCC) is a technological paradigm for providing services to mobile device (MD) users. A compromised MD may cause harm to both its user and to other MCC customers. This study explores the use of machine learning (ML) models and stochastic methods for the protection of Android MDs connected to the mobile cloud. To test the validity and feasibility of the proposed models and methods, the study adopted a proof-of-concept approach and developed a prototype system named MINDPRESS. The static component of MINDPRES assesses the risk of the apps installed on the MD. It uses a device-based ML model for static feature analysis and a cloud-based stochastic risk evaluator. The device-based hybrid component of MINDPRES monitors app behavior in real time. It deploys two ML models and functions as an intrusion detection and prevention system (IDPS). The performance evaluation results of the prototype showed that the accuracy achieved by the methods for static and hybrid risk evaluation compared well with results reported in recent work. Power consumption data indicated that MINDPRES did not create an overload. This study contributes a feasible and scalable framework for building distributed systems for the protection of the data and devices of MCC customers.