Search

In today’s digital landscape, critical services are increasingly dependent on network connectivity, thus cybersecurity has become paramount. Indeed, the constant escalation of cyberattacks, including zero-day exploits, poses a significant threat. While Network Intrusion Detection Systems (NIDSs) leveraging machine-learning and deep-learning models have proven effective in recent studies, they encounter limitations such as the need for abundant samples of malicious traffic and full retraining upon encountering new attacks. These limitations hinder their adaptability in real-world scenarios. To address these challenges, we design a novel NIDS capable of promptly adapting to classify new attacks and provide timely predictions. Our proposal for attack-traffic classification adopts Few-Shot Class-Incremental Learning (FSCIL) and is based on the Rethinking Few-Shot (RFS) approach, which we experimentally prove to overcome other FSCIL state-of-the-art alternatives based on either meta-learning or transfer learning. We evaluate the proposed NIDS across a wide array of cyberattacks whose traffic is collected in recent publicly available datasets to demonstrate its robustness across diverse network-attack scenarios, including malicious activities in an Internet-of-Things context and cyberattacks targeting servers. We validate various design choices as well, involving the number of traffic samples per attack available, the impact of the features used to represent the traffic objects, and the time to deliver the classification verdict. Experimental results witness that our proposed NIDS effectively retains previously acquired knowledge (with over 94% F1-score) while adapting to new attacks with only few samples available (with over 98% F1-score). Thus, it outperforms non-FSCIL state of the art in terms of classification effectiveness and adaptation time. Moreover, our NIDS exhibits high performance even with traffic collected within short time frames, achieving 95% F1-score while reducing the time-to-insight. Finally, we identify possible limitations likely arising in specific application contexts and envision promising research avenues to mitigate them.

Significant in lifestyle have reshaped the Internet landscape, resulting in notable shifts in both the magnitude of Internet traffic and the diversity of apps utilized. The increased adoption of communication-and-collaboration apps, also fueled by lockdowns in the COVID pandemic years, has heavily impacted the management of network infrastructures and their traffic. A notable characteristic of these apps is their multi-activity nature, e.g., they can be used for chat and (interactive) audio/video in the same usage session: predicting and managing the traffic they generate is an important but especially challenging task. In this study, we focus on real data from four popular apps belonging to the aforementioned category: Skype, Teams, Webex, and Zoom. First, we collect traffic data from these apps, reliably label it with both the app and the specific user activity and analyze it from the perspective of traffic prediction. Second, we design data-driven models to predict this traffic at the finest granularity (i.e., at packet level) employing four advanced multitask deep learning architectures and investigating three different training strategies. The trade-off between performance and complexity is explored as well. We publish the dataset and release our code as open source to foster the replicability of our analysis. Third, we leverage the packet-level prediction approach to perform aggregate prediction at different timescales. Fourth, our study pioneers the trustworthiness analysis of these predictors via the application of eXplainable Artificial Intelligence to $(a)$ interpret their forecasting results and $(b)$ evaluate their reliability, highlighting the relative importance of different parts of observed traffic and thus offering insights for future analyses and applications. The insights gained from the analysis provided with this work have implications for various network management tasks, including monitoring, planning, resource allocation, and enforcing security policies.

Software-Defined Networking (SDN) and Blockchain are leading technologies used worldwide to establish safe network communication as well as build secure network infrastructures. They provide a robust and reliable platform to address threats and face challenges such as security, privacy, flexibility, scalability, and confidentiality. Driven by these assumptions, this paper presents an optimized energy-efficient and secure Blockchain-based software-defined IoT framework for smart networks. Indeed, SDN and Blockchain technologies have proven to be able to suitably manage resource utilization and to develop secure network communication across the IoT ecosystem. However, there is a lack of research works that present a comprehensive definition of such a framework that can meet the requirements of the IoT ecosystem (i.e. efficient energy utilization and reduced end-to-end delay). Therefore, in this research, we present a layered hierarchical architecture for the deployment of a distributed yet efficient Blockchain-enabled SDN-IoT framework that ensures efficient cluster-head selection and secure network communication via the identification and isolation of rouge switches. Besides, the Blockchain-enabled flow-rules record keeps track of the rules enforced in the switches and maintains the consistency within the controller cluster. Finally, we assess the performance of the proposed framework in a simulation environment and show that it can achieve optimized energy-utilization, end-to-end delay, and throughput compared to considered baselines, thus being able to achieve efficiency and security in the smart network.

The internet of things is a worldwide technological development in communications. Low Power and Lossy Networks (LLN) are a fundamental part of the internet of things with numerous monitoring and controlling applications. This network has many challenges as well, due to limited hardware and communication resources, which causes problems in applications such as routing, connections, data transfer, and aggregation between nodes. The IETF group has provided a routing model for LLN networks, which expands IPv6 protocol based on Routing Protocol (RPL). The pro-posed decision system DDSLA-RPL creates a list of limited k member optimal parents based on qualitatively effective parameters such as hop, link quality, SNR rate, and ETX energy consumption, by informing child nodes of their connection link to available parents. In the routing section, a decision system approach based on learning automata has been proposed to dynamically determine and update the weight of influential parameters in routing. The effective parameters in the routing phase of DDSLA-RPL include battery depletion index, connection delay, and node queuing and throughput. The results of the simulation show that the proposed method outperforms other methods by about 30, 17, 20, 18, and 24 percent in mean longevity and energy efficiency, graph sustainability, operational power and latency, packet delivery rate test, and finally number of control messages test, respectively.

Cloud computing concepts offer effective and efficient tools for addressing resource-hungry computational problems. While conventional methods, architectures, and processing techniques may limit cloud data center performance, software-defined cloud computing (SDCC) is an approach where virtualization services to all network resources in a dc are software-defined and where software-defined networking (SDN) and cloud computing go hand in hand. SDCC-related concepts change the previous state of affairs by promoting the centralized control of networking functions in a data center. A key objective of developing software-driven cloud infrastructure is that the networking hardware, software, storage, security, and network traffic management is open and interoperable. This facilitates easy installation and management of networking functions in the cloud infrastructure. Employing SDCC concepts to cloud data centers can improve resource administration challenges to a greater extent. This paper presents a survey on SDCC. We begin by introducing SDCC environments and explain its main architectural components. We identify the essential contributions of various developments to this field and discuss the implementation challenges and limitations faced in their adoption. We also explore the potential of SDCC in two domains, namely, resource orchestration and application development, as case studies of specific interest. In an attempt to anticipate the future evolution, we discuss the important research opportunities and challenges in this promising field.

The population of cities is increasing day-by-day. According to United Nations, it is estimated that by 2050, 66% of the world’s population will live in cities [item 1) of the Appendix]. This is indicative of a drive to live in more privileged and smarter environments. Therefore, there exists an increased demand for intelligent and sustainable environments that offer citizens of urban areas a high quality life. Smart cities may be a solution. Millions of dedicated and reliable sensors are required in smart cities to enhance the quality of urban living. Communications infrastructure is inevitably required for connecting these sensors. In order to better manage urban resources, there exists a need to explore issues like deployment of sensors, communications technologies, information management, and defining and deploying proper smart city applications.