The rapid expansion of Internet of Things (IoT) devices has heightened the need for effective intrusion detection systems (IDS) that operate under strict resource constraints. Conventional IDS implementations require substantial computational resources, making them unsuitable for low-power microcontroller-based devices. This paper proposes a novel collaborative IDS architecture that separates centralised model training from distributed edge inference. The system employs an autoencoder-based labelling mechanism trained on regular traffic to identify anomalies. Each ESP32 device performs local inference and exchanges predictions via UDP multicast, whilst MD5 hashing ensures model consistency across the network. Collaborative verification enables devices to identify and isolate compromised nodes without central coordination. Experimental evaluation demonstrates 98.5% F-score with 3ms average inference latency and 12.7KB memory footprint, consuming only 2.4% of available SRAM. Our approach achieves superior detection accuracy compared to existing cloud-edge systems whilst operating on severely resource-constrained hardware, making it a practical solution for large-scale IoT security deployments.

The rapid growth of technology has increased interconnected large-scale systems, broadening the attack surface for malicious actors . Traditional security solutions often employ centralised management of components like firewalls and intrusion detection systems for consistent configuration. This centralisation introduces a ”single point of failure,” risking severe consequences if compromised. While redundancy can mitigate concerns in IT systems, it does not scale well for larger systems. Edge computing , which pushes computation closer to endpoint devices , has been explored to improve scalability. The research community has also explored distributing and decentralising cybersecurity operations, especially intrusion detection , using new machine learning methods that mix centralised and distributed approaches to scale effectively while preserving data privacy. However, challenges remain in implementing these methods in large-scale IoT systems due to resource constraints . This paper evaluates intrusion detection methods in large-scale, resource-limited IoT systems, exploring the benefits of low-powered devices for network security and discussing solutions to current implementation challenges.

Data integrity becomes paramount as the number of Internet of Things (ioT) sensor deployments increases. Sensor data can be altered by benign causes or malicious actions. Mechanisms that detect drifts and irregularities can prevent disruptions and data bias in the state of an IoT application. This paper presents LE3D, an ensemble framework of data drift estimators capable of detecting abnormal sensor behaviours. Working collaboratively with surrounding ioT devices, the type of drift (natural/abnormal) can also be identified and reported to the end-user. The proposed framework is a lightweight and unsupervised implementation able to run on resource-constrained IoT devices. Our framework is also generalisable, adapting to new sensor streams and environments with minimal online reconfiguration. We compare our method against state-of-the-art ensemble data drift detection frameworks, evaluating both the real-world detection accuracy as well as the resource utilisation of the implementation. Experimenting with real-world data and emulated drifts, we show the effectiveness of our method, which achieves up to 97% of detection accuracy while requiring minimal resources to run.

The vast increase of Internet of Things (IoT) technologies and the ever-evolving attack vectors have increased cyber-security risks dramatically. A common approach to implementing AI-based Intrusion Detection Systems (IDSs) in distributed IoT systems is in a centralised manner. However, this approach may violate data privacy and prohibit IDS scalability. Therefore, intrusion detection solutions in IoT ecosystems need to move towards a decentralised direction. Federated Learning (FL) has attracted significant interest in recent years due to its ability to perform collaborative learning while preserving data confidentiality and locality. Nevertheless, most FL-based IDS for IoT systems are designed under unrealistic data distribution conditions. To that end, we design an experiment representative of the real-world and evaluate the performance of an FL-based IDS. For our experiments, we rely on TON-IoT, a realistic IoT network traffic dataset, associating each IP address with a single FL client. Additionally, we explore pre-training and investigate various aggregation methods to mitigate the impact of data heterogeneity. Lastly, we benchmark our approach against a centralised solution. The comparison shows that the heterogeneous nature of the data has a considerable negative impact on the model's performance when trained in a distributed manner. However, in the case of a pre-trained initial global FL model, we demonstrate a performance improvement of over 20% (F1-score) compared to a randomly initiated global model.

Edge computing is rapidly changing the IoT-Cloud landscape. Various testbeds are now able to run multiple Docker-like containers developed and deployed by end-users on edge devices. However, this capability may allow an attacker to deploy a malicious container on the host and compromise it. This paper presents a dataset based on the Linux Auditing System, which contains malicious and benign container activity. We developed two malicious scenarios, a denial of service and a privilege escalation attack, where an adversary uses a container to compromise the edge device. Furthermore, we deployed benign user containers to run in parallel with the malicious containers. Container activity can be captured through the host system via system calls. Our time series auditd dataset contains partial labels for the benign and malicious related system calls. Generating the dataset is largely automated using a provided AutoCES framework. We also present a semi-supervised machine learning use case with the collected data to demonstrate its utility. The dataset and framework code are open-source and publicly available.

Complexity is ever increasing within our information environment and organisations, as interdependent dynamic relationships within sociotechnical systems result in high variety and uncertainty from a lack of information or control. A net-centric approach is a strategy to improve information value, to enable stakeholders to extend their reach to additional data sources, share Situational Awareness (SA), synchronise effort and optimise resource use to deliver maximum (or proportionate) effect in support of goals. This paper takes a systems perspective to understand the dynamics within a net-centric information system. This paper presents the first stages of the Soft Systems Methodology (SSM), to develop a conceptual model of the human activity system and develop a system dynamics model to represent system behaviour, that will inform future research into a net-centric approach with information security. Our model supports the net-centric hypothesis that participation within a information sharing community extends information reach, improves organisation SA allowing proactive action to mitigate vulnerabilities and reduce overall risk within the community. The system dynamics model provides organisations with tools to better understand the value of a net-centric approach, a framework to determine their own maturity and evaluate strategic relationships with collaborative communities.

In this paper we try to determine whether a potential state-aggressor in a recent cyber attack can be identified through an understanding of shared international dependencies between nations. Combining the International Affairs and Systems Science disciplines, we put forth a system dynamics model of cyber conflict which may facilitate the identification of a culpable state or states in a cyber attack through publicly available information. Having identified 22 countries with military or civilian cyber capability, data on economic trade imports and diplomatic relationships were combined to identify dependencies, or countries upon which dependent countries rely for trade or military collaboration. The system dynamics model simulates diplomatic tension between two countries to estimate the probability of a cyber conflict. Nine case studies, in which the likely cyber combatant was identified, are used to test the model. Initial results yielded a number of prior indicators of cyber conflict, such as dips in trade imports from future cyber combatants up to 2 years before a launched cyber attack.