Catálogo de publicaciones - revistas

<jats:p> Transformer model architectures have garnered immense interest lately due to their effectiveness across a range of domains like language, vision and reinforcement learning. In the field of natural language processing for example, Transformers have become an indispensable staple in the modern deep learning stack. Recently, a dizzying number of <jats:italic>“X-former”</jats:italic> models have been proposed - Reformer, Linformer, Performer, Longformer, to name a few - which improve upon the original Transformer architecture, many of which make improvements around computational and memory <jats:italic>efficiency</jats:italic> . With the aim of helping the avid researcher navigate this flurry, this paper characterizes a large and thoughtful selection of recent efficiency-flavored “X-former” models, providing an organized and comprehensive overview of existing work and models across multiple domains. </jats:p>

<jats:p>Cyberspace is full of uncertainty in terms of advanced and sophisticated cyber threats which are equipped with novel approaches to learn the system and propagate themselves, such as AI-powered threats. To debilitate these types of threats, a modern and intelligent Cyber Situation Awareness (SA) system needs to be developed which has the ability of monitoring and capturing various types of threats, analyzing, and devising a plan to avoid further attacks. This paper provides a comprehensive study on the current state-of-the-art in the cyber SA to discuss the following aspects of SA: key design principles, framework, classifications, data collection, analysis of the techniques, and evaluation methods. Lastly, we highlight misconceptions, insights, and limitations of this study and suggest some future work directions to address the limitations.</jats:p>

<jats:p>Data mining is the science of extracting information or ‘knowledge’ from data. It is a task commonly executed on cloud computing resources, personal computers and laptops. However, what about smartphones? Despite the fact that these ubiquitous mobile devices now offer levels of hardware and performance approaching that of laptops, locally executed model-training using data mining methods on smartphones is still notably rare. On-device model-training offers a number of advantages. It largely mitigates issues of data security and privacy, since no data is required to leave the device. It also ensures a self-contained, fully-portable data mining solution requiring no cloud computing or network resources and able to operate in any location. In this paper, we focus on the intersection of smartphones and data mining. We investigate the growth in smartphone performance, survey smartphone usage models in previous research and look at recent developments in locally-executed data mining on smartphones.</jats:p>

<jats:p>Multi-document summarization (MDS) is an effective tool for information aggregation that generates an informative and concise summary from a cluster of topic-related documents. Our survey, the first of its kind, systematically overviews the recent deep learning based MDS models. We propose a novel taxonomy to summarize the design strategies of neural networks and conduct a comprehensive summary of the state-of-the-art. We highlight the differences between various objective functions that are rarely discussed in the existing literature. Finally, we propose several future directions pertaining to this new and exciting field.</jats:p>

<jats:p>There any many different access control systems, yet a commonality is that they provide flexible mechanisms to enforce different access levels. Their importance in organisations to adequately restrict resources, coupled with their use in a dynamic environment, mandates the need to routinely perform policy analysis. The aim of performing analysis is often to identify potential problematic permissions, which have the potential to be exploited and could result in data theft and unintended modification. There is a vast body of published literature on analysing access control systems, yet as performing analysis has a strong end-user motivation and is grounded in security challenges faced in real-world systems, it is important to understand how research is developing, what are the common themes of interest, and to identify key challenges that should be addressed in future work. To the best of the authors’ knowledge, no survey has been performed to gain an understanding of empirical access control analysis, focussing on how techniques are evaluated and how they align to the needs of real-world analysis tasks. This article provides a systematic literature review, identifying and summarising key works. Key findings are identified and discussed as areas of future work.</jats:p>

<jats:p>Field Programmable Gate Arrays (FPGAs) are spatial architectures with a heterogenous reconfigurable fabric. They are state-of-the-art for prototyping, telecommunications, embedded, and an emerging alternative for cloud-scale acceleration. However, FPGA adoption found limitations in their programmability and required knowledge. Therefore, researchers focused on FPGA abstractions and automation tools. Here, we survey three leading digital design abstractions: Hardware Description Languages (HDLs), High-Level Synthesis (HLS) tools, and Domain-Specific Languages (DSLs). We review these abstraction solutions, provide a timeline, and propose a taxonomy for each abstraction trend: programming models for HDLs; IP-based or System-based toolchains for HLS; application, architecture, and infrastructure domains for DSLs.</jats:p>

<jats:p>With the continuous expansion of the Industrial Internet of Things (IIoT) and the increasing connectivity among the various intelligent devices or systems, the control of access and fusion in smart factory networks has significantly gained importance. However, the contradiction between the high Quality of Service (QoS) requirements of massive data and the limited network bandwidth and the heterogeneous network is becoming deeper and deeper. The heterogeneity of smart factory networks brings many challenges to unified access and fusion, real-time transmission, and centralized control and management. This paper provides a survey on heterogeneous networks in smart factories. We first study and discuss the heterogeneity of smart factory networks, and then discuss the existing mainstream wired and wireless network technologies, as well as promising future technologies, including 5G, OLE for Process Control Unified Architecture (OPC UA), and Time-Sensitive Networking (TSN). In addition, we also analyze current heterogeneous network fusion architecture and discuss the enabling technologies of heterogeneous network fusion in view of the shortcoming of the current solutions. Finally, we conclude with a discussion of open challenges and future research directions towards the effective realization of the smart factory.</jats:p>

<jats:p>In recent years, machine learning has transitioned from a field of academic research interest to a field capable of solving real-world business problems. However, the deployment of machine learning models in production systems can present a number of issues and concerns. This survey reviews published reports of deploying machine learning solutions in a variety of use cases, industries and applications and extracts practical considerations corresponding to stages of the machine learning deployment workflow. By mapping found challenges to the steps of the machine learning deployment workflow we show that practitioners face issues at each stage of the deployment process. The goal of this paper is to lay out a research agenda to explore approaches addressing these challenges.</jats:p>

<jats:p> As our epistemic ambitions grow, the common and scientific endeavours are becoming increasingly dependent on Machine Learning (ML). The field rests on a single experimental paradigm, which consists of splitting the available data into a training and testing set and using the latter to measure how well the trained ML model generalises to unseen samples. If the model reaches acceptable accuracy, then an <jats:italic>a posteriori</jats:italic> contract comes into effect between humans and the model, supposedly allowing its deployment to target environments. Yet the latter part of the contract depends on human inductive predictions or generalisations, which infer a uniformity between the trained ML model and the targets. The article asks how we justify the contract between human and machine learning. It is argued that the justification becomes a pressing issue when we use ML to reach “elsewhere” in space and time or deploy ML models in non-benign environments. The article argues that the only viable version of the contract can be based on optimality (instead of on reliability, which cannot be justified without circularity) and aligns this position with Schurz's optimality justification. It is shown that when dealing with inaccessible/unstable ground-truths (“elsewhere” and non-benign targets), the optimality justification undergoes a slight change, which should reflect critically on our epistemic ambitions. Therefore, the study of ML robustness should involve not only heuristics that lead to acceptable accuracies on testing sets. The justification of human inductive predictions or generalisations about the uniformity between ML models and targets should be included as well. Without it, the assumptions about inductive risk minimisation in ML are not addressed in full. </jats:p>

<jats:p>Voting is a formal expression of opinion or choice, either positive or negative, made by an individual or a group of individuals. However, conventional voting systems tend to be centralized, which are known to suffer from security and efficiency limitations. Hence, there has been a trend of moving to decentralized voting systems, such as those based on blockchain. The latter is a decentralized digital ledger in a peer-to-peer network, where a copy of the append-only ledger of digitally signed and encrypted transactions is maintained by each participant. Therefore, in this article, we perform a comprehensive review of blockchain-based voting systems and classify them based on a number of features (e.g., the types of blockchain used, the consensus approaches used, and the scale of participants). By systematically analyzing and comparing the different blockchain-based voting systems, we also identify a number of limitations and research opportunities. Hopefully, this survey will provide an in-depth insight into the potential utility of blockchain in voting systems and device future research agenda.</jats:p>