Federated learning (FL) is a popular approach to facilitate privacy-aware machine learning since it allows multiple clients to collaboratively train a global model without granting others access to their private data. It is, however, known that FL can be vulnerable to membership inference attacks (MIAs), where the training records of the global model can be distinguished from the testing records. Surprisingly, research focusing on the investigation of the source inference problem appears to be lacking. We also observe that identifying a training record's source client can result in privacy breaches extending beyond MIAs. For example, consider an FL application where multiple hospitals jointly train a COVID-19 diagnosis model, membership inference attackers can identify the medical records that have been used for training, and any additional identification of the source hospital can result the patient from the particular hospital more prone to discrimination. Seeking to contribute to the literature gap, we take the first step to investigate source privacy in FL. Specifically, we propose a new inference attack (hereafter referred to as source inference attack – SIA), designed to facilitate an honest-but-curious server to identify the training record's source client. The proposed SIAs leverage the Bayesian theorem to allow the server to implement the attack in a non-intrusive manner without deviating from the defined FL protocol. We then evaluate SIAs in three different FL frameworks to show that in existing FL frameworks, the clients sharing gradients, model parameters, or predictions on a public dataset will leak such source information to the server. We also conduct extensive experiments on various datasets to investigate the key factors in an SIA. The experimental results validate the efficacy of the proposed SIAs, e.g., an attack success rate of 67.1% (baseline 10%) can be achieved when the clients share model parameters with the server. Comprehensive ablation studies demonstrate that the success of an SIA is directly related to the overfitting of the local models.

By developing awareness of smartphone activities that the user is performing on their smartphone, such as scrolling feeds, typing and watching videos, we can develop application features that are beneficial to the users, such as personalization. It is currently not possible to access real-time smartphone activities directly, due to standard smartphone privileges and if internal movement sensors can detect them, there may be implications for access policies. Our research seeks to understand whether the sensor data from existing smartphone inertial measurement unit (IMU) sensors (triaxial accelerometers, gyroscopes and magnetometers) can be used to classify typical human smartphone activities. We designed and conducted a study with human participants which uses an Android app to collect motion data during scrolling, typing and watching videos, while walking or seated and the baseline of smartphone non-use, while sitting and walking. We then trained a machine learning (ML) model to perform real-time activity recognition of those eight states. We investigated various algorithms and parameters for the best accuracy. Our optimal solution achieved an accuracy of 78.6% with the Extremely Randomized Trees algorithm, data sampled at 50 Hz and 5-s windows. We conclude by discussing the viability of using IMU sensors to recognize common smartphone activities.

Background: Forecasting models predicting trends in hospitalization rates have the potential to inform hospital management during seasonal epidemics of respiratory diseases and the associated surges caused by acute hospital admissions. Hospital bed requirements for elective surgery could be better planned if it were possible to foresee upcoming peaks in severe respiratory illness admissions. Forecasting models can also guide the use of intervention strategies to decrease the spread of respiratory pathogens and thus prevent local health system overload. In this study, we explore the capability of forecasting models to predict the number of hospital admissions in Auckland, New Zealand, within a three-week time horizon. Furthermore, we evaluate probabilistic forecasts and the impact on model performance when integrating laboratory data describing the circulation of respiratory viruses. Methods: The dataset used for this exploration results from active hospital surveillance, in which the World Health Organization Severe Acute Respiratory Infection (SARI) case definition was consistently used. This research nurse-led surveillance has been implemented in two public hospitals in Auckland and provides a systematic laboratory testing of SARI patients for nine respiratory viruses, including influenza, respiratory syncytial virus, and rhinovirus. The forecasting strategies used comprise automatic machine learning, one of the most recent generative pre-trained transformers, and established artificial neural network algorithms capable of univariate and multivariate forecasting. Results: We found that machine learning models compute more accurate forecasts in comparison to naïve seasonal models. Furthermore, we analyzed the impact of reducing the temporal resolution of forecasts, which decreased the model error of point forecasts and made probabilistic forecasting more reliable. An additional analysis that used the laboratory data revealed strong season-to-season variations in the incidence of respiratory viruses and how this correlates with total hospitalization cases. These variations could explain why it was not possible to improve forecasts by integrating this data. Conclusions: Active SARI surveillance and consistent data collection over time enable these data to be used to predict hospital bed utilization. These findings show the potential of machine learning as support for informing systems for proactive hospital management.

Over the past decade, a large number of deductive object-oriented database languages have been proposed. The earliest of these languages had few object-oriented features, and more and more features have systematically been incorporated in successive languages. However, a language with a clean logical semantics that naturally accounts for all the key object-oriented features, is still missing from the literature. This article takes us another step towards solving this problem. Two features that are currently missing are the encapsulation of rule-based methods in classes, and nonmonotonic structural and behavioral inheritance with overriding, conflict resolution and blocking. This article introduces the syntax of a language with these features. The language is restricted in the sense that we have omitted other object-oriented and deductive features that are now well understood, in order to make our contribution clearer. It then defines a class of databases, called well-defined databases , that have an intuitive meaning and develops a direct logical semantics for this class of databases. The semantics is based on the well-founded semantics from logic programming. The work presented in this article establishes a firm logical foundation for deductive object-oriented databases.

In today's data-driven landscape, intelligent systems must continuously learn from evolving data streams while preserving previously acquired knowledge. Continual learning (CL) has emerged as a key paradigm to meet this need, offering the potential to build adaptable and resilient AI systems. Despite its promise, CL faces core challenges such as catastrophic forgetting (CF), which occurs when learning new tasks degrades prior knowledge. These challenges have spurred rapid growth in CL research and method development. This paper presents a systematic literature review (SLR) of CL research published from 2010 to 2025. We adopt a reproducible methodology that combines automated searches across five major databases with manual searches from 13 key venues, resulting in a curated set of 189 peer-reviewed papers. Our review fills key gaps in earlier surveys by unifying fragmented classifications, probing overlooked causes of catastrophic forgetting, and advancing a more principled theoretical framing of CL challenges beyond empirical benchmarking. We contribute by offering (1) an updated, comprehensive overview of CL research; (2) refined taxonomies of learning methods and settings; (3) an analysis of the structural and functional causes of CF; and (4) the identification of open theoretical questions and emerging research directions. We provide an open-source repository of the reviewed literature and associated resources to support ongoing work: https://github.com/yyy24601/awesome-continual-learning.