Catálogo de publicaciones - revistas

<jats:p>The prosperity of machine learning has been accompanied by increasing attacks on the training process. Among them, poisoning attacks have become an emerging threat during model training. Poisoning attacks have profound impacts on the target models, e.g., making them unable to converge or manipulating their prediction results. Moreover, the rapid development of recent distributed learning frameworks, especially federated learning, has further stimulated the development of poisoning attacks. Defending against poisoning attacks is challenging and urgent. However, the systematic review from a unified perspective remains blank. This survey provides an in-depth and up-to-date overview of poisoning attacks and corresponding countermeasures in both centralized and federated learning. We firstly categorize attack methods based on their goals. Secondly, we offer detailed analysis of the differences and connections among the attack techniques. Furthermore, we present countermeasures in different learning framework and highlight their advantages and disadvantages. Finally, we discuss the reasons for the feasibility of poisoning attacks and address the potential research directions from attacks and defenses perspectives, separately.</jats:p>

<jats:p>Perhaps the most straightforward classifier in the arsenal or Machine Learning techniques is the Nearest Neighbour Classifier—classification is achieved by identifying the nearest neighbours to a query example and using those neighbours to determine the class of the query. This approach to classification is of particular importance, because issues of poor runtime performance is not such a problem these days with the computational power that is available. This article presents an overview of techniques for Nearest Neighbour classification focusing on: mechanisms for assessing similarity (distance), computational issues in identifying nearest neighbours, and mechanisms for reducing the dimension of the data.</jats:p> <jats:p>This article is the second edition of a paper previously published as a technical report [16]. Sections on similarity measures for time-series, retrieval speedup, and intrinsic dimensionality have been added. An Appendix is included, providing access to Python code for the key methods.</jats:p>

<jats:p>During the past few years, research in applying machine learning (ML) to design efficient, effective, and robust metaheuristics has become increasingly popular. Many of those machine learning-supported metaheuristics have generated high-quality results and represent state-of-the-art optimization algorithms. Although various appproaches have been proposed, there is a lack of a comprehensive survey and taxonomy on this research topic. In this article, we will investigate different opportunities for using ML into metaheuristics. We define uniformly the various ways synergies that might be achieved. A detailed taxonomy is proposed according to the concerned search component: target optimization problem and low-level and high-level components of metaheuristics. Our goal is also to motivate researchers in optimization to include ideas from ML into metaheuristics. We identify some open research issues in this topic that need further in-depth investigations.</jats:p>

<jats:p>Intelligent transportation systems (ITS) enable transportation participants to communicate with each other by sending and receiving messages, so that they can be aware of their surroundings and facilitate efficient transportation through better decision making. As an important part of ITS, autonomous vehicles can bring massive benefits by reducing traffic accidents. Correspondingly, much effort has been paid to the task of pedestrian detection, which is a fundamental task for supporting autonomous vehicles. With the progress of computational power in recent years, adopting deep learning–based methods has become a trend for improving the performance of pedestrian detection. In this article, we present design guidelines on deep learning–based pedestrian detection methods for supporting autonomous vehicles. First, we will introduce classic backbone models and frameworks, and we will analyze the inherent attributes of pedestrian detection. Then, we will illustrate and analyze representative pedestrian detectors from occlusion handling, multi-scale feature extraction, multi-perspective data utilization, and hard negatives handling these four aspects. Last, we will discuss the developments and trends in this area, followed by some open challenges.</jats:p>

<jats:p>Nowadays, we are witnessing the advent of the Internet of Things (IoT) with numerous devices performing interactions between them or with their environment. The huge number of devices leads to huge volumes of data that demand the appropriate processing. The “legacy” approach is to rely on Cloud where increased computational resources can realize any desired processing. However, the need for supporting real-time applications requires a reduced latency in the provision of outcomes. Edge Computing (EC) comes as the “solver” of the latency problem. Various processing activities can be performed at EC nodes having direct connection with IoT devices. A number of challenges should be met before we conclude a fully automated ecosystem where nodes can cooperate or understand their status to efficiently serve applications. In this article, we perform a survey of the relevant research activities towards the vision of Edge Mesh (EM), i.e., a “cover” of intelligence upon the EC. We present the necessary hardware and discuss research outcomes in every aspect of EC/EM nodes functioning. We present technologies and theories adopted for data, tasks, and resource management while discussing how machine learning and optimization can be adopted in the domain.</jats:p>

<jats:p>Area under the ROC curve, a.k.a. AUC, is a measure of choice for assessing the performance of a classifier for imbalanced data. AUC maximization refers to a learning paradigm that learns a predictive model by directly maximizing its AUC score. It has been studied for more than two decades dating back to late 90s and a huge amount of work has been devoted to AUC maximization since then. Recently, stochastic AUC maximization for big data and deep AUC maximization (DAM) for deep learning have received increasing attention and yielded dramatic impact for solving real-world problems. However, to the best our knowledge there is no comprehensive survey of related works for AUC maximization. This paper aims to address the gap by reviewing the literature in the past two decades. We not only give a holistic view of the literature but also present detailed explanations and comparisons of different papers from formulations to algorithms and theoretical guarantees. We also identify and discuss remaining and emerging issues for DAM, and provide suggestions on topics for future work.</jats:p>

<jats:p>This paper offers a comprehensive review of the research on Natural Language Generation (NLG) over the past two decades, especially in relation to data-to-text generation and text-to-text generation deep learning methods, as well as new applications of NLG technology. This survey aims to (a) give the latest synthesis of deep learning research on the NLG core tasks, as well as the architectures adopted in the field; (b) detail meticulously and comprehensively various NLG tasks and datasets, and draw attention to the challenges in NLG evaluation, focusing on different evaluation methods and their relationships; (c) highlight some future emphasis and relatively recent research issues that arise due to the increasing synergy between NLG and other artificial intelligence areas, such as computer vision, text and computational creativity.</jats:p>

<jats:p>Honeyword (or decoy password) based authentication, first introduced by Juels and Rivest in 2013, has emerged as a security mechanism that can provide security against server-side threats on the password-files. From the theoretical perspective, this security mechanism reduces attackers’ efficiency to a great extent as it detects the threat on a password-file so that the system administrator can be notified almost immediately as an attacker tries to take advantage of the compromised file. This paper aims to present a comprehensive survey of the relevant research and technological developments in honeyword-based authentication techniques. We cover twenty-three techniques related to honeyword, reported under different research articles since 2013. This survey paper helps the readers to (i) understand how honeyword based security mechanism works in practice, (ii) get a comparative view on the existing honeyword based techniques, and (iii) identify the existing gaps that are yet to be filled and the emergent research opportunities.</jats:p>

<jats:p>The bioinformatics discipline seeks to solve problems in biology with computational theories and methods. Formal concept analysis (FCA) is one such theoretical model, based on partial orders. FCA allows the user to examine the structural properties of data based on which subsets of the data set depend on each other. This paper surveys the current literature related to the use of FCA for bioinformatics. The survey begins with a discussion of FCA, its hierarchical advantages, several advanced models of FCA, and lattice management strategies. It then examines how FCA has been used in bioinformatics applications, followed by future prospects of FCA in those areas. The applications addressed include gene data analysis (with next-generation sequencing), biomarkers discovery, protein-protein interaction, disease analysis (including COVID-19, cancer, and others), drug design and development, healthcare informatics, biomedical ontologies, and phylogeny. Some of the most promising prospects of FCA are: identifying influential nodes in a network representing protein-protein interactions, determining critical concepts to discover biomarkers, integrating machine learning and deep learning for cancer classification, and pattern matching for next-generation sequencing.</jats:p>

<jats:p>The Internet of Things (IoT) is impacting the world’s connectivity landscape. More and more IoT devices are connected, bringing many benefits to our daily lives. However, the influx of IoT devices poses non-trivial challenges for the existing cloud-based computing paradigm. In the cloud-based architecture, a large amount of IoT data is transferred to the cloud for data management, analysis, and decision making. It could not only cause a heavy workload on the cloud but also result in unacceptable network latency, ultimately undermining the benefits of cloud-based computing. To address these challenges, researchers are looking for new computing models for the IoT. Edge computing, a new decentralized computing model, is valued by more and more researchers in academia and industry. The main idea of edge computing is placing data processing in near-edge devices instead of remote cloud servers. It is promising to build more scalable, low-latency IoT systems. Many studies have been proposed on edge computing and IoT, but a comprehensive survey of this crossover area is still lacking.</jats:p> <jats:p>In this survey, we firstly introduce the impact of edge computing on the development of IoT and point out why edge computing is more suitable for IoT than other computing paradigms. Then, we analyze the necessity of systematical investigation on the edge-computing-driven IoT (ECDriven-IoT) and summarize new challenges occurred in ECDriven-IoT. We categorize recent advances from bottom to top, covering six aspects of ECDriven-IoT. Finally, we conclude lessons learned and propose some challenging and worthwhile research directions.</jats:p>