@isep.ipp.pt
Departamento de Engenharia Informática
ISEP/GECAD
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Tiago Fonseca, Tiago Dias, João Vitorino, Luís Lino Ferreira, and Isabel Praça
AIP Publishing
Hoon Ko, Isabel Praca, and Seong Gon Choi
Springer Science and Business Media LLC
AbstractVarious studies have been conducted to detect network anomalies. However, because anomaly signals are determined by the pattern characteristics using the dataset, the real-time detection problem continues. Even if there is a signal with an attack sign among the constantly transmitted and received signals, the attack cannot be blocked in advance. Moreover, it appears in many places in a distributed denial-of-service (DDoS) attack, so the real-time defense must be the best option. Therefore, it is necessary first to discover the characteristics and elements regarded as abnormal signals to discover anomalies in real time. Finally, by analyzing the correlation between network data and features, extracting the elements of the anomaly, and analyzing the behavior of the extracted elements in detail, we aim to increase the accuracy of the anomaly. In this study, we used Coburg intrusion detection and KDDCup datasets and analyzed the correlation of elements in the dataset using a graph neural network. The calculated accuracy values of the anomaly detection were 94.5% and 98.85%.
Tiago Fontes Dias, João Vitorino, Tiago Fonseca, Isabel Praça, Eva Maia, and Maria João Viamonte
Springer Nature Switzerland
João Vitorino, Isabel Praça, and Eva Maia
Elsevier BV
Tiago Dias, João Vitorino, Eva Maia, Orlando Sousa, and Isabel Praça
Elsevier BV
Eva Maia, Pedro Vieira, and Isabel Praça
MDPI AG
Chatbots have become increasingly popular in the healthcare industry. In the area of preventive care, chatbots can provide personalized and timely solutions that aid individuals in maintaining their well-being and forestalling the development of chronic conditions. This paper presents GECA, a chatbot designed specifically for preventive care, that offers information, advice, and monitoring to patients who are undergoing home treatment, providing a cost-effective, personalized, and engaging solution. Moreover, its adaptable architecture enables extension to other diseases and conditions seamlessly. The chatbot’s bilingual capabilities enhance accessibility for a wider range of users, including those with reading or writing difficulties, thereby improving the overall user experience. GECA’s ability to connect with external resources offers a higher degree of personalization, which is a crucial aspect in engaging users effectively. The integration of standards and security protocols in these connections allows patient privacy, security and smooth adaptation to emerging healthcare information sources. GECA has demonstrated a remarkable level of accuracy and precision in its interactions with the diverse features, boasting an impressive 97% success rate in delivering accurate responses. Presently, preparations are underway for a pilot project at a Portuguese hospital that will conduct exhaustive testing and evaluate GECA, encompassing aspects such as its effectiveness, efficiency, quality, goal achievability, and user satisfaction.
João Vitorino, Isabel Praça, and Eva Maia
Springer Science and Business Media LLC
Abstract The internet of things (IoT) faces tremendous security challenges. Machine learning models can be used to tackle the growing number of cyber-attack variations targeting IoT systems, but the increasing threat posed by adversarial attacks restates the need for reliable defense strategies. This work describes the types of constraints required for a realistic adversarial cyber-attack example and proposes a methodology for a trustworthy adversarial robustness analysis with a realistic adversarial evasion attack vector. The proposed methodology was used to evaluate three supervised algorithms, random forest (RF), extreme gradient boosting (XGB), and light gradient boosting machine (LGBM), and one unsupervised algorithm, isolation forest (IFOR). Constrained adversarial examples were generated with the adaptative perturbation pattern method (A2PM), and evasion attacks were performed against models created with regular and adversarial training. Even though RF was the least affected in binary classification, XGB consistently achieved the highest accuracy in multi-class classification. The obtained results evidence the inherent susceptibility of tree-based algorithms and ensembles to adversarial evasion attacks and demonstrate the benefits of adversarial training and a security-by-design approach for a more robust IoT network intrusion detection and cyber-attack classification.
Artemisa R. Dores, Miguel Peixoto, Maria Castro, Catarina Sá, Irene P. Carvalho, Andreia Martins, Eva Maia, Isabel Praça, and António Marques
MDPI AG
The increased consumption of a variety of herbs/supplements has been raising serious health concerns. Owing to an inadequate understanding of herb/supplement–drug interactions, the simultaneous consumption of these products may result in deleterious effects and, in extreme cases, even fatal outcomes. This systematic review is aimed at understanding the knowledge and beliefs about the consumption of herbs/supplements and herb/drug–supplement interactions (HDIs). The study follows the PRISMA guidelines. Four online databases (Web of Science; PubMed; Cochrane; and EBSCOhost) were searched, and a total of 44 studies were included, encompassing 16,929 participants. Herb and supplement consumption is explained mostly by the reported benefits across multiple conditions and ease of use. Regarding HDIs, most people take both herbs/supplements and prescription drugs simultaneously. Only a small percentage of participants have knowledge about their interaction effects, and many reported adverse interactions or side effects. Nevertheless, the main reason for stopping the prescribed drug intake is the perceived lack of its effect, and not due to interactions. Therefore, it is important to increase the knowledge about supplement use so that further strategies can be elaborated to better detect or be alert for whenever a potentially dangerous reaction and/or interaction may occur. This paper raises awareness regarding the need for developing a decision support system and ends with some considerations about the development of a technological solution capable of detecting HDIs and, thereby, aiding in the improvement of pharmacy services.
Ivone Amorim, Pedro Barbosa, Eva Maia, and Isabel Praça
Springer Nature Switzerland
Tiago Dias, Arthur Batista, Eva Maia, and Isabel Praça
Springer Nature Switzerland
Ivone Amorim, Eva Maia, Pedro Barbosa, and Isabel Praça
Springer Nature Switzerland
Tiago Dias, Tiago Fonseca, João Vitorino, Andreia Martins, Sofia Malpique, and Isabel Praça
Springer Nature Switzerland
Luís Mata, Sinan Wannous, David Duarte, Eva Maia, Pedro Vieira, and Isabel Praça
IEEE
Over the past decade, the technological evolution of mobile networks has contributed to the global success and democratization of internet connectivity, notably relying on 4G and 5G deployments. Digital services have grown exponentially, resulting in high traffic volumes and continuous requirements to expand the network footprint. The problem is that, despite the investment in network expansion and upgrade, the revenues of the major Mobile Network Operators (MNOs) have presented anaemic growth, whilst other factor costs have risen, notably the energy prices. This challenging outlook raises concerns over the sector’s long-term sustainability and calls MNOs to adopt smart operative strategies in network management, aiming at ensuring sustainable energy consumption levels. This new paradigm essentially leverages artificial intelligence capabilities to evolve the current reactive approach of Network Operations Centres (NOCs) towards proactive and preventive models relying on network data. In particular, energy consumption data can be used to detect abnormal network behaviours, either caused by unintentional disruptions or by a cyber/physical attack. This paper contributes with a novel multi-domain NOC that combines performance, efficiency and security as an integral part of network optimization. Additionally, as a concrete use case example using live data from a 4G mobile network, a new methodology is proposed to optimize the trade-off between spectral and energy efficiency. The preliminary results show that up to 13% of improvement in energy consumption could be achieved using the proposed methodology to detect the worse performing sites and their root cause factors.
José Tavares, Pedro Brandão, Ivo Barros, Jose Gonçalves, Isabel Praça, Lucia Lacerda, and Marisa Santos
IEEE
Machine learning is an area of Artificial Intelligence in which applying algorithms to a dataset makes it possible to predict results or even discover relationships that would be unnoticeable at first glance. Currently the amount of information available in different areas, especially in health care where data collection and analysis seek to define personalized medicine strategies. This is a field where using Machine Learning-based tools can assume a relevant role. This work presents a study of diverse classification algorithms in the area of machine learning applied to identification of amino acid profiles. The authors defined as a major objective to develop a new biomarker profile for prediction and prognosis of rectal cancer. The data involved in the training of classification algorithms refer to patients with metabolic diseases and rectal cancer. The best machine learning classification models will be tested to achieve the most effective decision support system for a most adequate treatment option selection in order to reduce the morbidity and mortality rate.
João Vitorino, Lourenço Rodrigues, Eva Maia, Isabel Praça, and André Lourenço
Springer Nature Switzerland
João Vitorino, Tiago Dias, Tiago Fonseca, Nuno Oliveira, and Isabel Praça
Springer International Publishing
Nuno Oliveira, Norberto Sousa, and Isabel Praça
Springer International Publishing
Eva Maia, Sinan Wannous, Tiago Dias, Isabel Praça, and Ana Faria
MDPI AG
The accelerating transition of traditional industrial processes towards fully automated and intelligent manufacturing is being witnessed in almost all segments. This major adoption of enhanced technology and digitization processes has been originally embraced by the Factories of the Future and Industry 4.0 initiatives. The overall aim is to create smarter, more sustainable, and more resilient future-oriented factories. Unsurprisingly, introducing new production paradigms based on technologies such as machine learning (ML), the Internet of Things (IoT), and robotics does not come at no cost as each newly incorporated technique poses various safety and security challenges. Similarly, the integration required between these techniques to establish a unified and fully interconnected environment contributes to additional threats and risks in the Factories of the Future. Accumulating and analyzing seemingly unrelated activities, occurring simultaneously in different parts of the factory, is essential to establish cyber situational awareness of the investigated environment. Our work contributes to these efforts, in essence by envisioning and implementing the SMS-DT, an integrated platform to simulate and monitor industrial conditions in a digital twin-based architecture. SMS-DT is represented in a three-tier architecture comprising the involved data and control flows: edge, platform, and enterprise tiers. The goal of our platform is to capture, analyze, and correlate a wide range of events being tracked by sensors and systems in various domains of the factory. For this aim, multiple components have been developed on the basis of artificial intelligence to simulate dominant aspects in industries, including network analysis, energy optimization, and worker behavior. A data lake was also used to store collected information, and a set of intelligent services was delivered on the basis of innovative analysis and learning approaches. Finally, the platform was tested in a textile industry environment and integrated with its ERP system. Two misuse cases were simulated to track the factory machines, systems, and people and to assess the role of SMS-DT correlation mechanisms in preventing intentional and unintentional actions. The results of these misuse case simulations showed how the SMS-DT platform can intervene in two domains in the first scenario and three in the second one, resulting in correlating the alerts and reporting them to security operators in the multi-domain intelligent correlation dashboard.
Eva Maia, Norberto Sousa, Nuno Oliveira, Sinan Wannous, Orlando Sousa, and Isabel Praça
MDPI AG
Critical infrastructures are an attractive target for attackers, mainly due to the catastrophic impact of these attacks on society. In addition, the cyber–physical nature of these infrastructures makes them more vulnerable to cyber–physical threats and makes the detection, investigation, and remediation of security attacks more difficult. Therefore, improving cyber–physical correlations, forensics investigations, and Incident response tasks is of paramount importance. This work describes the SMS-I tool that allows the improvement of these security aspects in critical infrastructures. Data from heterogeneous systems, over different time frames, are received and correlated. Both physical and logical security are unified and additional security details are analysed to find attack evidence. Different Artificial Intelligence (AI) methodologies are used to process and analyse the multi-dimensional data exploring the temporal correlation between cyber and physical Alerts and going beyond traditional techniques to detect unusual Events, and then find evidence of attacks. SMS-I’s Intelligent Dashboard supports decision makers in a deep analysis of how the breaches and the assets were explored and compromised. It assists and facilitates the security analysts using graphical dashboards and Alert classification suggestions. Therefore, they can more easily identify anomalous situations that can be related to possible Incident occurrences. Users can also explore information, with different levels of detail, including logical information and technical specifications. SMS-I also integrates with a scalable and open Security Incident Response Platform (TheHive) that enables the sharing of information about security Incidents and helps different organizations better understand threats and proactively defend their systems and networks.
Norberto Sousa, Nuno Oliveira, and Isabel Praça
MDPI AG
The Internet, much like our universe, is ever-expanding. Information, in the most varied formats, is continuously added to the point of information overload. Consequently, the ability to navigate this ocean of data is crucial in our day-to-day lives, with familiar tools such as search engines carving a path through this unknown. In the research world, articles on a myriad of topics with distinct complexity levels are published daily, requiring specialized tools to facilitate the access and assessment of the information within. Recent endeavors in artificial intelligence, and in natural language processing in particular, can be seen as potential solutions for breaking information overload and provide enhanced search mechanisms by means of advanced algorithms. As the advent of transformer-based language models contributed to a more comprehensive analysis of both text-encoded intents and true document semantic meaning, there is simultaneously a need for additional computational resources. Information retrieval methods can act as low-complexity, yet reliable, filters to feed heavier algorithms, thus reducing computational requirements substantially. In this work, a new search engine is proposed, addressing machine reading at scale in the context of scientific and academic research. It combines state-of-the-art algorithms for information retrieval and reading comprehension tasks to extract meaningful answers from a corpus of scientific documents. The solution is then tested on two current and relevant topics, cybersecurity and energy, proving that the system is able to perform under distinct knowledge domains while achieving competent performance.
João Vitorino, Nuno Oliveira, and Isabel Praça
MDPI AG
Adversarial attacks pose a major threat to machine learning and to the systems that rely on it. In the cybersecurity domain, adversarial cyber-attack examples capable of evading detection are especially concerning. Nonetheless, an example generated for a domain with tabular data must be realistic within that domain. This work establishes the fundamental constraint levels required to achieve realism and introduces the adaptative perturbation pattern method (A2PM) to fulfill these constraints in a gray-box setting. A2PM relies on pattern sequences that are independently adapted to the characteristics of each class to create valid and coherent data perturbations. The proposed method was evaluated in a cybersecurity case study with two scenarios: Enterprise and Internet of Things (IoT) networks. Multilayer perceptron (MLP) and random forest (RF) classifiers were created with regular and adversarial training, using the CIC-IDS2017 and IoT-23 datasets. In each scenario, targeted and untargeted attacks were performed against the classifiers, and the generated examples were compared with the original network traffic flows to assess their realism. The obtained results demonstrate that A2PM provides a scalable generation of realistic adversarial examples, which can be advantageous for both adversarial training and attacks.
Andreia Martins, Eva Maia, and Isabel Praca
IEEE
Complementary and alternative medicine are commonly used concomitantly with conventional medications leading to adverse drug reactions and even fatality in some cases. Furthermore, the vast possibility of herb-drug interactions prevents health professionals from remembering or manually searching them in a database. Decision support systems are a powerful tool that can be used to assist clinicians in making diagnostic and therapeutic decisions in patient care. Therefore, an original and hybrid decision support system was designed to identify herb-drug interactions, applying artificial intelligence techniques to identify new possible interactions. Different machine learning models will be used to strengthen the typical rules engine used in these cases. Thus, using the proposed system, the pharmacy community, people’s first line of contact within the Healthcare System, will be able to make better and more accurate therapeutic decisions and mitigate possible adverse events.
Sinan Wannous, Tiago Dias, Eva Maia, Isabel Praça, and Ana Raquel Faria
Springer International Publishing