In the context of large-scale data collection like in the Internet of Things, Data Confidence Fabrics are expected to play an essential role in verifying and authenticating sensor data. To this end, metadata is generated at each network node and stored on the blockchain. However, storing metadata on the blockchain introduces significant privacy risks, as it can be exploited to reveal sensitive information, such as network structures and communication paths. This paper addresses these challenges by proposing two novel schemes to protect network structures: Hostname Mapping and Hostname Encryption . Our work demonstrates that the Hostname Mapping approach effectively conceals network patterns but introduces inefficiencies due to additional table storage and computational overhead. In contrast, the Hostname Encryption method eliminates the need for additional table management, offering a more efficient and secure alternative. Despite these advancements, the timestamp field in metadata could still allow attackers to infer patterns using machine learning, highlighting the need for further research to fully secure metadata. By combining encryption with some enhancements to timestamp obfuscation, our approach lays the foundation for additional privacy protection against metadata exploitation.

Data Confidence Fabrics (DCFs) are emerging as a mechanism to obtain measurable trust in decentralized smart computing environments, while remote attestation (RA) is being established as a key mechanism for verifying security in distributed systems. However, both of these approaches remain underutilized in container orchestration platforms, resulting in inadequate trust guarantees, increased attack surface areas, and insufficient mechanisms for verifying the integrity of devices and applications. In this paper, we propose leveraging DCFs to integrate RA with software security practices, and utilizing this integration to securely onboard devices and containerized applications by tracing their provenance and analyzing vulner-abilities. This dual-level protection bridges device attestation measurements with measurements of application security to provide measurable and transparent confidence scores for both. The proposed approach brings trustworthiness into a distributed environment where devices are continuously monitored for malicious tampering, and applications are assessed before being run. We verified this approach on a setup representing real environments. Additionally, a machine learning model was put under test and trained on data weighted with confidence scores produced by our proposed approach. The model saw improved performance and accuracy, showing that this approach can increase the reliability of systems.

The need to trust data has become a key requirement in modern distributed systems. To facilitate measurable trust and confidence in data and applications spanning heterogeneous systems, the emerging concept of a Data Confidence Fabric (DCF) offers a compelling solution. Data producers and processors provide metadata, known as annotations, recording trust insertion along the data delivery chain. Thus, it is possible to asses the trustworthiness of data before processing it. While a DCF, such as the Alvarium framework, enables this management of trust, there is a cost in terms of the overheads associated with security annotations themselves. To improve efficiency of a DCF, we therefore propose a set of techniques for making annotations more compact and to reduce the number of DCF transactions. Our work shows that transaction efficiency gains of up to 93% in our considered use cases can be achieved.

In distributed environments, data for Machine Learning (ML) applications may be generated from numerous sources and devices, and traverse a cloud-edge continuum via a variety of protocols, using multiple security schemes and equipment types. While ML models typically benefit from using large training sets, not all data can be equally trusted. In this work, we examine data trust as a factor in creating ML models, and explore an approach using annotated trust metadata to contribute to data weighting in generating ML models. We assess the feasibility of this approach using well-known datasets for both linear regression and classification problems, demonstrating the benefit of including trust as a factor when using heterogeneous datasets. We discuss the potential benefits of this approach, and the opportunity it presents for improved data utilisation and processing.

To find missing people in a remote area, we propose an autonomous unmanned aerial vehicle (UAV) approach which attempts to locate the target by detecting and localising the radio signals produced by a GSM cell phone. By using a low- weight software defined radio and companion computer, the UAV can act as a GSM base station and induce the missing person's device to attempt to make contact. Through the signal strength values and known UAV location, a series of these contact attempts can be used to quickly and accurately localise their position. As the area in which the missing person might be located may be quite large, and the interaction of radio signals with terrain is potentially complex, an efficient search strategy for exploring the area is required in order to reduce time taken to make contact. We make use of a constraint-based graph-based path planning approach to produce a route for the UAV to traverse in the air passing through expected signals from a large number of possible source locations, and demonstrate through experiments the timely identification and localisation of the cell phone.

Simulation of building evacuations can be a powerful tool for predicting evacuation outcomes, but for this prediction to be useful it must be produced in a timely manner. The building evacuation outcomes are dependent on the movement decisions of the occupants, but simulating all possible combinations of occupant decisions is infeasible. Our contribution is a novel technique using building structure knowledge in the form of a Network Flow Graph to determine where and when occupants might interact with one another. We decompose the problem into non-interacting groups, to be simulated separately, which leads to a significant simulation workload reduction.