Catálogo de publicaciones - revistas

<jats:p>With the increasing proliferation of hardware accelerators and the predicted continued increase in the heterogeneity of future computing systems, it is necessary to understand the security properties of such systems. In this survey article, we consider the security of heterogeneous systems against microarchitectural attacks, with a focus on covert- and side-channel attacks, as well as fault injection attacks. We review works that have explored the vulnerability of the individual accelerators (such as Graphical Processing Units, GPUs and Field Programmable Gate Arrays, FPGAs) against these attacks, as well as efforts to mitigate them. We also consider the vulnerability of other components within a heterogeneous system such as the interconnect and memory component. We believe that this survey is especially timely, as new accelerators and heterogeneous systems are being designed such that these designs understand the security threats and develop systems that are not only performant but also secure.</jats:p>

<jats:p>Dynamic fuzzy characteristics are ubiquitous in a lot of scientific and engineering problems. Specifically, the physical systems and learning processes in machine learning are dynamic and fuzzy in general. This fact has driven researchers to integrate dynamic elements into fuzzy theory and proposed dynamic fuzzy sets and dynamic fuzzy logic. Based on these pioneering theoretical works and various theories for uncertain datasets, an innovative machine learning paradigm which is referred to as dynamic fuzzy machine learning (DFML) was proposed in the early 2000s. DFML extends existing fuzzy machine learning paradigms to deal with dynamic fuzzy problems in machine learning activities. This article provides an insightful overview of DFML by surveying the field from basics to advances in five aspects: (1) the theoretical basics; (2) the system and the learning model; (3) typical DFML methods and categorization of the methods; (4) the open challenges; and (5) the research frontiers. As the first survey addressing the topic, this paper intends to help more researchers better understand the basics and state-of-the-art in this field, find the most appropriate tools for a particular application, and identify possible directions for future research.</jats:p>

<jats:p>Anomaly analysis is an important component of any surveillance system. In recent years, it has drawn the attention of the computer vision and machine learning communities. In this article, our overarching goal is thus to provide a coherent and systematic review of state-of-the-art techniques and a comprehensive review of the research works in anomaly analysis. We would like to provide a broad vision of computational models, datasets, metrics, extensive experiments, and what anomaly analysis can do in images and videos. Intensively covering nearly 200 publications we review i) anomaly related surveys, ii) taxonomy for anomaly problems, iii) the computational models, iv) the benchmark datasets for studying abnormalities in images and videos, and v) the performance of state-of-the-art methods in this research problem. In addition, we provide insightful discussions and pave way to the future work.</jats:p>

<jats:p>Multimodal classification research has been gaining popularity with new datasets in domains such as satellite imagery, biometrics, and medicine. Prior research has shown the benefits of combining data from multiple sources compared to traditional unimodal data which has led to the development of many novel multimodal architectures. However, the lack of consistent terminologies and architectural descriptions makes it difficult to compare different solutions. We address these challenges by proposing a new taxonomy for describing multimodal classification models based on trends found in recent publications. Examples of how this taxonomy could be applied to existing models are presented as well as a checklist to aid in the clear and complete presentation of future models. Many of the most difficult aspects of unimodal classification have not yet been fully addressed for multimodal datasets including big data, class imbalance, and instance level difficulty. We also provide a discussion of these challenges and future directions of research.</jats:p>

<jats:p>Recommender systems (RSs) have become an inseparable part of our everyday lives. They help us find our favorite items to purchase, our friends on social networks, and our favorite movies to watch. Traditionally, the recommendation problem was considered to be a classification or prediction problem, but it is now widely agreed that formulating it as a sequential decision problem can better reflect the user-system interaction. Therefore, it can be formulated as a Markov decision process (MDP) and be solved by reinforcement learning (RL) algorithms. Unlike traditional recommendation methods, including collaborative filtering and content-based filtering, RL is able to handle the sequential, dynamic user-system interaction and to take into account the long-term user engagement. Although the idea of using RL for recommendation is not new and has been around for about two decades, it was not very practical, mainly because of scalability problems of traditional RL algorithms. However, a new trend has emerged in the field since the introduction of deep reinforcement learning (DRL), which made it possible to apply RL to the recommendation problem with large state and action spaces. In this paper, a survey on reinforcement learning based recommender systems (RLRSs) is presented. Our aim is to present an outlook on the field and to provide the reader with a fairly complete knowledge of key concepts of the field. We first recognize and illustrate that RLRSs can be generally classified into RL- and DRL-based methods. Then, we propose an RLRS framework with four components, i.e., state representation, policy optimization, reward formulation, and environment building, and survey RLRS algorithms accordingly. We highlight emerging topics and depict important trends using various graphs and tables. Finally, we discuss important aspects and challenges that can be addressed in the future.</jats:p>

<jats:p>Continuous Authentication (CA) technologies enable users to be authenticated beyond just the point of entry. In this article, we conduct a comprehensive review of over 2300 articles to (a) identify the main components of CA research to date, and (b) explore the current gaps and future research directions. Through a Citation Network Analysis (CNA), we identified that there are currently three primary focus research areas on CA - Keystroke Dynamics; Mouse Movements; and Mobile Device Touch, as well as identify an emerging trend in more recent studies on multi-modal CA authentication which utilises the numerous sensors that are embedded in modern mobile devices. This study also highlights the current gaps in the literature such as the need for a consensus over how to evaluate the application and utility of CA, and the need to examine the feasibility of CA technologies that currently exist based on more use case studies.</jats:p>

<jats:p>Machine learning components are essential for today’s software systems, causing a need to adapt traditional software engineering practices when developing machine-learning-based systems. This need is pronounced due to many development-related challenges of machine learning components such as asset, experiment, and dependency management. Recently, many asset management tools addressing these challenges have become available. It is essential to understand the support such tools offer to facilitate research and practice on building new management tools with native supports for machine learning and software engineering assets.</jats:p> <jats:p>This article positions machine learning asset management as a discipline that provides improved methods and tools for performing operations on machine learning assets. We present a feature-based survey of 18 state-of-practice and 12 state-of-research tools supporting machine-learning asset management. We overview their features for managing the types of assets used in machine learning experiments. Most state-of-research tools focus on tracking, exploring, and retrieving assets to address development concerns such as reproducibility, while the state-of-practice tools also offer collaboration and workflow-execution-related operations. In addition, assets are primarily tracked intrusively from the source code through APIs and managed via web dashboards or command-line interfaces. We identify asynchronous collaboration and asset reusability as directions for new tools and techniques.</jats:p>

<jats:p>Data augmentation, the artificial creation of training data for machine learning by transformations, is a widely studied research field across machine learning disciplines. While it is useful for increasing a model's generalization capabilities, it can also address many other challenges and problems, from overcoming a limited amount of training data, to regularizing the objective, to limiting the amount data used to protect privacy. Based on a precise description of the goals and applications of data augmentation and a taxonomy for existing works, this survey is concerned with data augmentation methods for textual classification and aims to provide a concise and comprehensive overview for researchers and practitioners. Derived from the taxonomy, we divide more than 100 methods into 12 different groupings and give state-of-the-art references expounding which methods are highly promising by relating them to each other. Finally, research perspectives that may constitute a building block for future work are provided.</jats:p>

<jats:p>Fog computing, as a distributed paradigm, offers cloud-like services at the edge of the network with low latency and high-access bandwidth to support a diverse range of IoT application scenarios. To fully utilize the potential of this computing paradigm, scalable, adaptive, and accurate scheduling mechanisms and algorithms are required to efficiently capture the dynamics and requirements of users, IoT applications, environmental properties, and optimization targets. This paper presents a taxonomy of recent literature on scheduling IoT applications in Fog computing. Based on our new classification schemes, current works in the literature are analyzed, research gaps of each category are identified, and respective future directions are described.</jats:p>

<jats:p>In recent years, aspect category detection has become popular due to the rapid growth in customer reviews data on e-commerce and other online platforms. Aspect Category Detection, a sub-task of Aspect-Based Sentiment Analysis, categorizes the reviews based on the features of a product such as a laptop’s display, or an aspect of an entity such as the restaurant’s ambiance. Various methods have been proposed to deal with such a problem. In this paper, we first introduce several datasets in the community that deal with this task and take a closer look at them by providing some exploratory analysis. Then, we review a number of representative methods for aspect category detection and classify them into two main groups: 1) supervised learning, and 2) unsupervised learning. Next, we discuss the strengths and weaknesses of different kinds of methods, which are expected to benefit both practical applications and future research. Finally, we discuss the challenges, open problems, and future research directions.</jats:p>