Cybersecurity threats in the Health sector are increasing globally due to the rising value of sensitive health information and availability of digitalised personal health records. This systematic review compares international and Australian health system cybersecurity landscapes in relation to the introduction of universal electronic health records. It examines recent trends in healthcare cybersecurity breaches that can disrupt essential services if patient safety and privacy are compromised. Often health systems and health mangers are ill-equipped to mitigate such threats. Recommendations are provided to proactively mature the cybersecurity culture within healthcare organisations, thus increasing their resilience to cyber threat.

Consumer groups are pressuring modern farmers to be more efficient with a focus on better animal welfare. Herding risks farmer lives, involves stress from farm dogs, and if not performed often and intelligently, risks neglect. We examined the behavioural and physiological response of twelve Dorper sheep (Ovies aries) to a drone to adapt mathematical models of shepherding to the new dimension. The model aims to make it feasible for artificial intelligence to improve the autonomy of farmers and pilots in shepherding from the sky. Sheep acclimatised quickly and positively to the drone initiating drive of a flock, regardless of drone speed. Our results demonstrate that stimulating sheep auditory awareness during herding from the sky leads to varying sheep responses. When controlled, these auditory cues can maintain safer distances between the drone and the sheep, offering great potential for the agriculture industry. We outline our ongoing research plans to achieve more autonomous sky shepherding that is compassionate to animal welfare and trusted by farmers and the consuming public.

This study investigates the effectiveness of simulator-based training systems in enhancing human drone piloting skills and performance. The study utilized a true-experimental research design to assess the impact of simulation training on accuracy, efficiency, and workload perception among human drone pilots. Leveraging historical simulation practices in conventional crewed aviation and incorporating instructivist educational principles, this research evaluates the potential for structured simulator training to improve real-world drone operation proficiency. Performance evaluation was focused upon the precision with which the participants were able to return the aircraft to a defined point in space after conducting a standard flight maneuver. Results indicate a significant improvement in flight performance among participants undergoing simulator training, reflected in a 32% reduction in mean final displacement. This highlights the value of integrating advanced simulation technologies and instructivist methodologies into drone pilot training programs to meet the evolving needs of both industry and academia.

Artificial intelligence (AI) has demonstrated success across various industries; however, its adoption in aviation remains limited due to concerns regarding the interpretability of AI models, which often function as black box systems with opaque decision-making processes. Given the safety-critical nature of aviation, the lack of transparency in AI-generated predictions poses significant challenges for industry stakeholders. This study investigates the classification performance of multiple supervised machine learning models and employs SHapley Additive exPlanations (SHAPs) to provide global model explanations, identifying key features that influence decision boundaries. To address the issue of class imbalance in the Australian Transport Safety Bureau (ATSB) dataset, a Variational Autoencoder (VAE) is also employed for data augmentation. A comparative evaluation of four machine learning algorithms is conducted for a three-class classification task:—Support Vector Machine (SVM), Logistic Regression (LR), Random Forest (RF), and a deep neural network (DNN) comprising five hidden layers. The results demonstrate a competitive performance across accuracy, precision, recall, and F1-score metrics, highlighting the effectiveness of explainable AI techniques in enhancing model transparency and fostering trust in AI-driven aviation safety applications.

Over the last three decades, defence communication and information systems have been increasing the complexity and interconnectedness of systems that has pervaded society more broadly throughout the Information Age. Even more than society in the broad, Western Departments of Defence (DoDs) have sought to attain information dominance. The result has been a large number of complex systems, system-of-systems and families-of-system-of-systems. In seeking to assure such interconnected systems, defence forces initially focused on specifying the high-level functions that this interconnectivity enabled: first command and control (1970s), then adding communications and computers (1980s) and finally adding intelligence, surveillance and reconnaissance (1990s); all while defining connections through interoperability protocols. The ability of highly interconnected systems to enable higher order human thinking has arguably gone beyond functions and even the informational, leading to synthetic systems. Furthermore, evolving cyber threats are now seeking to exploit the vulnerabilities of the broad informational attack surfaces of these complex DoD systems. This paper examines the key assurance initiatives pursued by the U.S. DoD to effect these more integrated, interoperable and information-assured (I3) capabilities while ensuring resilience to cyber threats. These approaches are compared to the Australian DoD’s assurance strategies and recommendations made on how Australia could substantially recover I3 assurance with the U.S. and other allied forces. The contrast between the two allies makes this a useful reflection for DoDs in other countries, and more generally to society’s assurance strategies.