Fog computing providers have started providing services in closer proximity to the users by leasing the unused computational resources of users' devices. The leased devices are increasingly used for many time-sensitive and IoT applications. Despite the advantages of Fog, due to the highly mobile and dynamic nature of Fog devices, the resources or devices may fail at any time or may not always be available for the processing of the applications, which leads to degradation of service quality and an increase in application processing time. Hence, effective selection of the resources in the Fog computing environment by considering mobility, heterogeneity, and failure of devices is a complex task. Traditional resource selection techniques may not be applied directly in Fog computing environments due to their dynamic and unique resource characteristics. Therefore, this article proposes a Markov chain-based resource selection model to improve the quality of service by minimizing disruptions and managing device failures. The effectiveness of the proposed algorithm is evaluated using simulations, which take failure traces, current resource usage, and mobility as input from a dataset archive. Our results demonstrate the effectiveness of the proposed algorithm in terms of average disruption rates, average latency, and average overutilization. Our analysis shows significant improvements in average latency reduction of approximately 11.83%, and an average overutilization improvement by 16.17%.

To address the growing threats of Zero-Day attacks, we propose an advanced intrusion detection system framework that integrates a GAMO model for data balancing and a Double DQN mechanism for dynamic sample selection. Unlike existing methods relying on static thresholds, our framework continuously adjusts its sampling strategies based on changing threat landscapes, thereby enhancing Zero-Day attack detection and improving the recognition of minority classes in imbalanced datasets. We validate the proposed framework using the CICIDS2017 dataset. In binary classification experiments, our approach achieves 99.66% accuracy, outperforming multiple baseline models. The GAMO component enhances the detection rates for minority attack classes.

As networks become more complex and interconnected, they grow more vulnerable to sophisticated cyberattacks. CyberBattleSim provides a simulation platform for modeling complex attack-defense interactions. This paper presents a real-time defense framework based on deep reinforcement learning, integrating Proximal Policy Optimization (PPO) and Asynchronous Advantage Actor-Critic (A3C). While prior research has primarily focused on improving attacker strategies such as Rapid ActorCritic (RAC) and Double Deep Q-Learning (DDQL), this work shifts attention to defender adaptability. The proposed Parallel Proximal Policy Optimization (PPPO) framework combines PPO’s policy stability with A3C’s asynchronous parallelism to enable rapid adaptation to evolving threats. Simulation results demonstrate that PPPO outperforms baseline approaches, including Deep Q-Learning and random policies in terms of cumulative rewards and network availability. Notably, PPPO maintains high availability even under multiple attacker scenarios. Real-time evaluations reveal a peak response latency of 0.005 seconds when utilizing five parallel agents. Comparative experiments further highlight the efficiency of GPU-based implementations, which achieve significantly faster training than CPU-based versions. These findings underscore the effectiveness and scalability of PPPO in enabling adaptive, autonomous defense mechanisms. This study contributes to advancing deep reinforcement learning applications in cybersecurity by providing a robust and real-time defense strategy capable of mitigating unknown and dynamic attacks in complex network environments.

Smart home applications are becoming increasingly popular due to their ability to provide safety, comfort, and remote assistance. These applications are usually controlled using a smart home controller, which is often the target of malware attacks. A successful attack may result in financial loss, disclosure of personal and/or sensitive information, or even loss of human lives. Although existing research has employed machine learning models to detect various malware attacks in smart home systems, they haven’t directly tackled the issue of class imbalance in this domain. In addition, the use of ensemble learners is expected to provide improved performance. To address this, we investigated different oversampling techniques to increase the number of samples in the minority classes and incorporated ensemble learners to see their impact on the prediction performance. Experimental evaluation indicates a marked enhancement of 4-5% across metrics, encompassing accuracy, precision, recall, and the F-1 score.

The (logically) centralized architecture of software-defined networks makes them an easy target for packet injection attacks. In these attacks, the attacker injects malicious packets into the SDN network to affect the services and performance of the SDN controller and overflows the capacity of the SDN switches. Such attacks have been shown to ultimately stop the network functioning in real-time, leading to network breakdowns. There have been significant works on detecting and defending against similar DoS attacks in non-SDN networks, but detection and protection techniques for SDN against packet injection attacks are still in their infancy. Furthermore, many of the proposed solutions have been shown to be easily bypassed by simple modifications to the attacking packets or by altering the attacking profile. In this paper, we develop novel Graph Convolutional Neural Network models and algorithms for grouping network nodes/users into security classes by learning from network data. We start with two simple classes - nodes that engage in suspicious packet injection attacks and nodes that are not. From these classes, we then partition the network into separate segments with different security policies using distributed Ryu controllers in an SDN network. We show in experiments on an emulated SDN that our detection solution outperforms alternative approaches with above 99% detection accuracy for various types (both old and new) of injection attacks. More importantly, our mitigation solution maintains continuous functions of non-compromised nodes while isolating compromised/suspicious nodes in real-time. All code and data are publicly available for the reproducibility of our results.

In the file sharing ecosystem, One-Click File Hosting Services (FHS) such as Rapidgator and Uploaded, the previously Rapidshare and Megaupload, provide a platform for users to share copyrighted content. We present a publisher-side analysis of FHS file sharing dynamics through data collected from active measurement by crawling Warez-BB. The website is essentially a forum where publishers can share links to content they have uploaded on file hosting services. Consumers can use the website to gain access to content shared on the website, often free of charge. We primarily analyse various characteristics of file sharing with respect to view count as the evaluation metric.

This paper aims to develop a real-time Plant Environment Simulator (PES), which simulates a corrugated plant effectively and realistically. The resultant solution of this work can be used to provide factory workers or new developers with a responsive, simulated learning environment on teaching how to use existing software correctly. The work is carried out for a large cardbox maker that can be used to test new prototypes without using the actual plant facilities, so it will economically and efficiently contribute to the creation of new robust software products for the corrugated plant.

Cultural venues like museums increasingly seek to harness the value of data analytics to make data driven decisions related to exhibitions duration, marketing campaigns, resource planning, and revenue optimization. One key priority is the need to understand the influencing factors behind visitor attendance. Using data collected from a large museum, we investigated whether the weather has a significant impact on visitor attendance or that other factors are more important. We applied the Cross Industry Standard Process for Data Mining (CRISP-DM) methodology to perform the research, developed and built four different types of regression models using R and its machine learning packages to model visitor attendance. The models were trained and evaluated. Predictions of visitor attendance were then generated from each of the four models and forecast accuracy was measured. The extreme gradient boost model was the best model with the highest average forecast accuracy of 93% and lowest forecast variability when benchmarked against the actual visitor attendance from the test data set. The weather was not considered to be as significant in predicting visitor trends and numbers to the museum compared to factors like time of the day, day of the week and school holidays. However, it was still measured to have a slight impact as excluding weather variables resulted in a model with a poorer fit. Weather can potentially have a more marked impact on cultural attractions in more extreme weather environments and outdoor venues.

Summary With the proliferation of Internet of Things (IoT) and edge computing paradigms, billions of IoT devices are being networked to support data‐driven and real‐time decision making across numerous application domains, including smart homes, smart transport, and smart buildings. These ubiquitously distributed IoT devices send the raw data to their respective edge device (eg, IoT gateways) or the cloud directly. The wide spectrum of possible application use cases make the design and networking of IoT and edge computing layers a very tedious process due to the: (i) complexity and heterogeneity of end‐point networks (eg, Wi‐Fi, 4G, and Bluetooth); (ii) heterogeneity of edge and IoT hardware resources and software stack; (iv) mobility of IoT devices; and (iii) the complex interplay between the IoT and edge layers. Unlike cloud computing, where researchers and developers seeking to test capacity planning, resource selection, network configuration, computation placement, and security management strategies had access to public cloud infrastructure (eg, Amazon and Azure), establishing an IoT and edge computing testbed that offers a high degree of verisimilitude is not only complex, costly, and resource‐intensive but also time‐intensive. Moreover, testing in real IoT and edge computing environments is not feasible due to the high cost and diverse domain knowledge required in order to reason about their diversity, scalability, and usability. To support performance testing and validation of IoT and edge computing configurations and algorithms at scale, simulation frameworks should be developed. Hence, this article proposes a novel simulator IoTSim‐Edge, which captures the behavior of heterogeneous IoT and edge computing infrastructure and allows users to test their infrastructure and framework in an easy and configurable manner. IoTSim‐Edge extends the capability of CloudSim to incorporate the different features of edge and IoT devices. The effectiveness of IoTSim‐Edge is described using three test cases. Results show the varying capability of IoTSim‐Edge in terms of application composition, battery‐oriented modeling, heterogeneous protocols modeling, and mobility modeling along with the resources provisioning for IoT applications.

Fog computing is a promising computing paradigm in which IoT data can be processed near the edge to support time-sensitive applications. However, the availability of resources in computation devices is not stable, since they may not be exclusively dedicated to the Fog application processing in the Fog environment. This, combined with dynamic user behaviour, can affect the execution of applications. To address dynamic changes in user behaviour in resource-limited Fog devices, this article proposes a multi-criteria–based resource allocation policy with resource reservation to minimise overall delay, processing time, and SLA violations. This process considers Fog computing–related characteristics, such as device heterogeneity, resource constraints, and mobility, as well as dynamic changes in user requirements. We employ multiple objective functions to find appropriate resources for executing time-sensitive tasks in the Fog environment. Experimental results show that our proposed policy performs better than the existing one, reducing the total delay by 51%. The proposed algorithm also reduces processing time and SLA violations, which is beneficial for running time-sensitive applications in the Fog environment.