Loading...
15 results
Search Results
Now showing 1 - 10 of 15
- Benchmarking bioinspired machine learning algorithms with CSE-CIC-IDS2018 network intrusions datasetPublication . Ferreira, Paulo; Antunes, MárioThis paper aims to evaluate CSE-CIC-IDS2018 network intrusions dataset and benchmark a set of supervised bioinspired machine learning algo rithms, namely CLONALG Artificial Immune System, Learning Vector Quantization (LVQ) and Back-Propagation Multi-Layer Perceptron (MLP). The results obtained were also compared with an ensemble strategy based on a majority voting algorithm. The results obtained show the appropri ateness of using the dataset to test behaviour based network intrusion de tection algorithms and the efficiency of MLP algorithm to detect zero-day attacks, when comparing with CLONALG and LVQ.
- Gestão de projectos TI e administração centralizada de sistemas e redes: cenários práticos em contexto empresarialPublication . Antunes, MárioO crescimento exponencial do número de redes e computadores interligados, verificado a partir de meados da década de 80, bem como a globalização dos mercados e a massificação e popularização da Internet, registada nas décadas seguintes, tornou as organizações altamente dependentes de tecnologias de informação e comunicação. Esta dependência tornou-as reféns de uma infra-estrutura de rede, servidores e serviços, que se pretendia segura, fiável e com mecanismos eficientes de mitigação das falhas. Este facto obrigou as organizações, em especial as empresas, a investirem continuamente em tecnologias de hardware e software que respondessem às necessidades do negócio, bem como a contratarem profissionais na área de administração e gestão de sistemas, servidores e redes. Nesta área as competências necessárias são vastas e abarcam conhecimentos multi-disciplinares. Genericamente, pretende-se que estes profissionais assegurem duas missões principais. Por um lado, o diagnóstico e a resolução de problemas. Por outro, a implementação de soluções técnicas avançadas que dotem a infra-estrutura de características distintivas de desempenho, segurança e disponibilidade, entre outros aspectos. Este relatório descreve o meu percurso profissional realizado em contexto empresarial, no período compreendido entre 1988 e 2001, enquanto quadro de várias empresas do grupo Sonae. Durante esse período desempenhei as funções de administrador e gestor de sistemas e redes, nomeadamente de tecnologias proprietárias da IBM (S/36 e S/38), de VAX-VMS e em sistemas Unix (IBM AIX, HP-UX e Linux). Fui igualmente gestor de projectos na área de Tecnologias de Informação em negócios críticos do grupo Sonae. Nesse sentido, tive a meu cargo a coordenação de vários projectos de implementação e gestão de redes de média e grande dimensão, bem como a implementação de soluções de alta disponibilidade em negócios críticos da Sonae Distribuição, recorrendo a tecnologias de clustering de servidores Unix. O documento inicia com uma descrição sumária do contexto empresarial em que se desenrolou a actividade, detalhando-se as tecnologias envolvidas e as topologias de rede geridas. Posteriormente, sintetizam-se os principais conceitos associados à temática da alta disponibilidade em redes, nomeadamente a identificação dos pontos críticos de falha e as várias formas de os mitigar. Concretamente no âmbito da implementação de clusters de alta disponibilidade, são identificados os principais conceitos associados e a metodologia para a sua construção. De seguida são detalhados três projectos principais onde tive responsabilidades de coordenação e gestão: implementação de um tradutor de EDI; implementação da nova plataforma operacional da gestão de entrepostos da Sonae Distribuição; implementação de uma solução centralizada de backups. Em cada um deles são enquadrados os principais conceitos técnicos e detalhada a solução implementada. De seguida tecem-se algumas considerações gerais à actividade desenvolvida no período em análise e ao estado actual dos projectos descritos. Por fim, descreve-se a integração da actividade desenvolvida em contexto empresarial com o período posterior a 2001, onde tenho desempenhado as funções de docente no ensino superior politécnico público.
- Desafios da gestão e segurança dos dados nas empresasPublication . Antunes, Mário
- TAT-NIDS: An Immune-Based Anomaly Detection Architecture for Network Intrusion DetectionPublication . Antunes, Mário; Correia, Manuel; Antunes, Mário;One emergent, widely used metaphor and rich source of inspiration for computer security has been the vertebrate Immune System (IS). This is mainly due to its intrinsic nature of having to constantly protect the body against harm inflicted by external (non-self) harmful entities. The bridge between metaphor and the reality of new practical systems for anomaly detection is cemented by recent biological advancements and new proposed theories on the dynamics of immune cells by the field of theoretical immunology. In this paper we present a work in progress research on the deployment of an immune-inspired architecture, based on Grossman's Tunable Activation Threshold (TAT) hypothesis, for temporal anomaly detection, where there is a strict temporal ordering on the data, such as network intrusion detection. We start by briefly describing the overall architecture. Then, we present some preliminary results obtained in a production network. Finally, we conclude by presenting the main lines of research we intend to pursue in the near future.
- An Artificial Immune System for Temporal Anomaly Detection Using Cell Activation Thresholds and Clonal Size Regulation with HomeostasisPublication . Antunes, Mário; Correia, Manuel E.This paper presents an Artificial Immune System (AIS) based on Grossman's Tunable Activation Threshold (TAT) for anomaly detection. We describe the immunological metaphor and the algorithm adopted for T-cells, emphasizing two important features: the temporal dynamic adjustment of T-cells clonal size and its associated homeostasis mechanism. We present some promising results obtained with artificially generated data sets, aiming to test the appropriateness of using TAT in dynamic changing environments, to distinguish new unseen patterns as part of what should be detected as normal or as anomalous.
- Adaptive learning for dynamic environments: A comparative approachPublication . Costa, Joana; Silva, Catarina; Antunes, Mário; Ribeiro, BernardeteNowadays most learning problems demand adaptive solutions. Current challenges include temporal data streams, drift and non-stationary scenarios, often with text data, whether in social networks or in business systems. Various efforts have been pursued in machine learning settings to learn in such environments, specially because of their non-trivial nature, since changes occur between the distribution data used to define the model and the current environment. In this work we present the Drift Adaptive Retain Knowledge (DARK) framework to tackle adaptive learning in dynamic environments based on recent and retained knowledge. DARK handles an ensemble of multiple Support Vector Machine (SVM) models that are dynamically weighted and have distinct training window sizes. A comparative study with benchmark solutions in the field, namely the Learn++.NSE algorithm, is also presented. Experimental results revealed that DARK outperforms Learn++.NSE with two different base classifiers, an SVM and a Classification and Regression Tree (CART).
- Evaluating cybersecurity attitudes and behaviors in Portuguese healthcare institutionsPublication . Nunes, Paulo; Antunes, Mário; Silva, CarinaThe growing digitization of healthcare institutions and its increasing dependence on Internet infrastructure has boosted the concerns related to data privacy and confidentiality. These institutions have been challenged with specific issues, namely the sensitivity of data, the specificity of networked equipment, the heterogeneity of healthcare professionals (nurses, doctors, administrative staff and other) and the IT skills they have.
- Cybersecurity risk analysis in healthcare institutionsPublication . Nunes, P; Antunes, M; Silva, CIntroduction The growing digitization of businesses and its increasing dependence on Internet infrastructure has boosted the concerns related to data privacy and confidentiality. Healthcare institutions have been challenged with specific issues, namely the sensitivity of data, the specificity of networked equipment and the average information technology skills held by of healthcare professionals in Portugal.
- Cybersecurity and Digital Forensics – Course Development in a Higher Education InstitutionPublication . Antunes, Mário; Rabadão, CarlosIndividuals and companies have a feeling of insecurity in the Internet, as every day a reasonable amount of attacks take place against users’ privacy and confidentiality. The use of digital equipment in illicit and unlawful activities has increasing. Attorneys, criminal polices, layers and courts staff have to deal with crimes committed with digital “weapons”, whose evidences have to be examined and reported by applying digital forensics methods. Digital forensics is a recent and fast-growing area of study which needs more graduated professionals. This fact has leveraged higher education institutions to develop courses and curricula to accommodate digital forensics topics and skills in their curricular offers. This paper aims to present the development of a cybersecurity and digital forensics master course in Polytechnic of Leiria, a public higher education institution in Portugal. The authors depict the roadmap and the general milestones that lead to the development of the course. The strengths and opportunities are identified and the major students’ outcomes are pointed out. The way taken and the decisions made are also approached, with a view to understanding the performance obtained so far.
- Identification of Fake Profiles in Twitter Social NetworkPublication . Antunes, Mário; Baptista, Hugo; Rodrigues, BaltazarOnline social networks are being intensively used by millions of users, Twitter being one of the most popular, as a powerful source of information with impact on opinion and decision making. However, in Twitter as in other online social networks, not all the users are legitimate, and it is not easy to detect those accounts that correspond to fake profiles. In this work in progress paper, we propose a method to help practitioners to identify fake Twitter accounts, by calculating the “fake probability” based on a weighted parameter set collected from public Twitter accounts. The preliminary results obtained with a subset of an existing annotated dataset of Twitter accounts are promising and give confidence on using this method as a decision support system, to help practitioners to identify fake profiles.