Contemporary Artificial Intelligence methods, especially their subset-deep learning, are finding their way to successful implementations in the detection and classification of intrusions at the network level. This paper presents an intrusion detection mechanism that leverages Deep AutoEncoder and several Deep Decoders for unsupervised classification. This work incorporates multiple network topology setups for comparative studies. The efficiency of the proposed topologies is validated on two established benchmark datasets: UNSW-NB15 and NetML-2020. The results of their analysis are discussed in terms of classification (...) accuracy, detection rate, false-positive rate, negative predictive value, Matthews correlation coefficient and F1-score. Furthermore, comparing against the state-of-the-art methods used for network intrusion detection is also disclosed. (shrink)

Countering the fake news phenomenon has become one of the most important challenges for democratic societies, governments and non-profit organizations, as well as for the researchers coming from several domains. This is not a local problem and demands a holistic approach to analyzing heterogeneous data and storing the results. The research problem we face in this paper is the proposition of an innovative distributed architecture to tackle the above-mentioned problems. The architecture uses state-of-the-art technologies with a focus on efficiency, scalability (...) and also openness, so that community-created components and digital content analyzers could be added. Moreover, we prove the usability of the prototype on Kaggle Fake News dataset. In particular, we consider different configurations of the proposed deep neural network and present the results reflecting the effectiveness, scalability and transferability of the proposed solution. (shrink)