No abstract

No abstract

our work on the recognition stage, taking the detected face as the input to the algorithm. This stage can be separated We developed an EBGM-based algorithm that successin two steps: feature extraction, where important inforfully implements face recognition under constrained condimation for discrimination is saved, and the matching step, tions. A suitable adaptation of the Gaborfilters was foundwhere the recognition result is given with the aid of a face through a power spectral analisys (PSD) of the face imdatabase. ages. We outperformed the best-known implementations of Several face recognition methods have been proposed the EBGM algorithm in the FERET database. The results are during the last thirty years. In the vast literature on the topic comparable with those of the state of the art.(see [15] for a review), there are different classifications of the existing techniques. The following is one posible highlevel classification:

With the ever-growing occurrence of networking attacks, robust network security systems are essential to prevent and mitigate their harming effects. In recent years, machine learning-based systems have gain popularity for network security applications, usually considering the application of shallow models, where a set of expert handcrafted features are needed to pre-process the data before training. The main problem with this approach is that handcrafted features can fail to perform well given different kinds of scenarios and problems. Deep Learning models can solve this kind of issues using their ability to learn feature representations from input raw or basic, non-processed data. In this paper we explore the power of deep learning models on the specific problem of detection and classification of malware network traffic, using different representations for the input data. As a major advantage as compared to the state of the art, we consider raw measurements coming directly from the stream of monitored bytes as the input to the proposed models, and evaluate different raw-traffic feature representations, including packet and flow-level ones. Our results suggest that deep learning models can better capture the underlying statistics of malicious traffic as compared to classical, shallow-like models, even while operating in the dark, i.e., without any sort of expert handcrafted inputs.