Multi-Agent Reinforcement Learning (MARL) is susceptible to Adversarial Machine Learning (AML) attacks. Execution-time AML attacks against MARL are complex due to effects that propagate across time and between agents. To understand the interaction between AML and MARL, this survey covers attacks and defences for MARL, Multi-Agent Learning (MAL), and Deep Reinforcement Learning (DRL). This survey proposes a novel perspective on AML attacks based on attack vectors. This survey also proposes a framework that addresses gaps in current modelling frameworks and enables the comparison of different attacks against MARL. Lastly, the survey identifies knowledge gaps and future avenues of research.

Performance anomaly detection is crucial for long running, large scale distributed systems. However, existing works focus on the detection of specific types of anomalies, rely on historical failure data, and cannot adapt to changes in system behavior at run time. In this work, we propose an adaptive framework for the detection and identification of complex anomalous behaviors, such as deadlocks and livelocks, in distributed systems without historical failure data. Our framework employs a two-step process involving two online SVM classifiers on periodically collected system metrics to identify at run time normal and anomalous behaviors such as deadlock, livelock, unwanted synchronization, and memory leaks. Our approach achieves over 0.70 F-score in detecting previously unseen anomalies and 0.78 F-score in identifying the type of known anomalies with a short delay after the anomalies appear, and with minimal expert intervention. Our experimental analysis uses system execution traces from our in-house distributed system with varied behaviors and a dataset by Yahoo!, and shows the benefits of our approach as well as future research challenges.

Worldwide, half of women begin a pregnancy with overweight or obesity, which increases the risk of pregnancy and birth complications and adversely affects the lifelong health of the offspring. In order for metabolic changes to influence the gestational environment, research suggests that weight loss should take place before conception. This study aimed to understand women’s emotional and social contexts, knowledge, motivations, skills and self-efficacy in making healthy change. Semi-structured interviews conducted with twenty-three women with overweight or obesity, informed by the Information–Motivation–Behavioural Skills (IMB) model, were analysed using reflexive thematic analysis. Information-related themes identified included poor health risk knowledge, healthy food decisions and health versus convenience. The Motivation themes comprised taking responsibility, flexible options, social expectations, interpersonal challenges and accountability. Behavioural Skills entailed themes such as the mental battle, time management, self-care and inspiration. An environmental factor was identified in affordability—limiting access to healthier alternatives. Women wanted simple, flexible options that considered family commitments, time and budgetary constraints. Unprompted, several mentioned the importance of psychological support in managing setbacks, stress and maintaining motivation. Strategies for enhancing self-efficacy and motivational support are required to enable longstanding health behaviour change. Findings will inform intervention mapping development of an eHealth solution for women preconception.

The use of established and discipline-specific theories within research and practice is an indication of the maturity of a discipline. With computing education research as a relatively young discipline, there has been recent interest in investigating theories that may prove foundational to work in this area, with discipline-specific theories and many theories from other disciplines emerging as relevant. A challenge for the researcher is to identify and select the theories that provide the best foundation for their work. Learning is a complex and multi-faceted process and, as such, a plethora of theories are potentially applicable to a research problem. Knowing the possible candidate theories and understanding their relationships and potential applicability, both individually or as a community of theories, is important to provide a comprehensive grounding for researchers and practitioners alike. In this work, we investigate the fundamental connections between learning theories foundational to research and practice in computing education. We build a comprehensive list of 84 learning theories and their source and influential papers, which are the papers that introduce or propagate specific theories within the research community. Using Scopus, ACM Digital Library, and Google Scholar, we identify the papers that cite these learning theories. We subsequently consider all possible pairs of these theories and build the set of papers that cite each pair. On this weighted graph of learning theory connections, we perform a community analysis to identify groups of closely linked learning theories. We find that most of the computing education learning theories are closely linked with a number of broader learning theories, forming a separate cluster of 17 learning theories. We build a taxonomy of theory relationships to identify the depth of connections between learning theories. Of the 294 analysed links, we find deep connections in 32 links. This indicates that while the computing education research community is aware of a large number of learning theories, there is still a need to better understand how learning theories are connected and how they can be used together to benefit computing education research and practice.

Simulation has become, in many application areas, a sine qua non . Most recently, COVID-19 has underlined the importance of simulation studies and limitations in current practices and methods. We identify four goals of methodological work for addressing these limitations. The first is to provide better support for capturing, representing, and evaluating the context of simulation studies, including research questions, assumptions, requirements, and activities contributing to a simulation study. In addition, the composition of simulation models and other simulation studies’ products must be supported beyond syntactical coherence, including aspects of semantics and purpose, enabling their effective reuse. A higher degree of automating simulation studies will contribute to more systematic, standardized simulation studies and their efficiency. Finally, it is essential to invest increased effort into effectively communicating results and the processes involved in simulation studies to enable their use in research and decision making. These goals are not pursued independently of each other, but they will benefit from and sometimes even rely on advances in other sub-fields. In this article, we explore the basis and interdependencies evident in current research and practice and delineate future research directions based on these considerations.