Joao Paulo Abreu Maranhao

After detecting a malicious artifact, classifying malware into specific families becomes an essential step to understand the threat's behavior, implement mitigation strategies, and develop proactive defenses. This task is particularly challenging due to the diversity of malware formats, the rapid evolution of obfuscation and packing techniques, as well as the scarcity of labeled data for training robust models. Additionally, the high volume of samples generated daily demands solutions that combine high accuracy and computational efficiency. Although transformer-based models are widely recognized as the state-of-the-art for sequence processing tasks, their high computational demands limit their practical application in resource-constrained environments. In this work, we present FORTUNATE, a lightweight framework that leverages LSTM networks with one-hot encoding to classify malware based on variable-length opcode sequences. The framework adopts an optimized opcode extraction process focused on reducing redundancies and representing data in compact vectors, minimizing computational costs. Experimental results indicate that FORTUNATE achieves accuracies of 99.82% for active malware and 99.81% for inactive malware, with an average classification time of only 56 ms per sample, significantly outperforming related works. The obtained results demonstrate that lightweight artificial intelligence approaches can deliver competitive performance in malware classification, especially in scenarios with computational constraints. FORTUNATE not only fills an important gap in malware classification but also establishes a foundation for future research aimed at optimizing the balance between accuracy, efficiency, and scalability.

Visual evoked potential (VEP) plays a crucial role in the diagnosis of nerve diseases and epilepsy. By applying luminous stimulation in different frequencies, neuronal electrical voltage changes are measured in the visual cortex area at the rear of the head using magnetoencephalogram (MEG). Such acquired MEG signals are separated into components using blind source separation (BSS). The MEG measurements are analyzed by medical experts and, based on their subjective interpretation, the VEP components are identified. Supervised machine learning (ML) methods can be applied to identify VEP components. However, these methods require labeled data, which must be generated through the subjective interpretation of medical experts. This can be limiting as medical experts traditionally assume a fixed amount of components. This paper proposes a blind framework to estimate the model order of the MEG measurements and to extract the VEP components. In order to estimate the amount of components, the framework exploits a low computational complexity modified Akaike Information Criterion (AIC) and does not require human intervention. In order to overcome the need for labeled data, we propose three approaches to automatically compare components extracted from MEG measurements with and without stimulation. Since each proposed unsupervised identification approach identifies a set of VEP components, we propose their decision fusion using set operations. The proposed framework does not require any human intervention, and it can be used as a complementary tool to support experts in identifying VEP components. The results are presented in terms of average amplitude spectrum and spectral topography. The proposed framework is validated using real MEG measurements.

Distributed Denial of Service (DDoS) attacks are one of the most challenging security threats, since a single victim is attacked by several compromised malicious nodes. As a consequence, legitimate end users can be prevented to access network resources. This letter proposes a noise-robust multilayer perceptron (MLP) architecture for DDoS attack detection trained with corrupted data. In the proposed approach, the average value of the common features among dataset instances is iteratively filtered out by applying Higher Order Singular Value Decomposition (HOSVD) based techniques. The effectiveness of the proposed architecture is validated through comparison with state-of-the-art methods.

Drones or unmanned aerial vehicles (UAV) are remotely piloted aircrafts which are very popular for commercial and public-safety applications. However, they can impose several security threats such as espionage and terrorism-related activities. In this way, we propose a multidimensional antenna array based framework in order to accurately localize UAVs in multipath environments. Specifically, we extend a previous framework for signal emitter localization in two aspects: (i) by adopting a tensor representation to better exploit the structure inherently multidimensional of the data, and (ii) by including a multiple denoising preprocessing scheme to increase the signal-to-noise ratio of the received signal. Numerical results show that the proposed approach presents both lower position coordinate errors and spatial frequency errors when compared to the matrix-based and tensor-based techniques with spatial smoothing as denoising preprocessing step.

Visual Evoked Potential (VEP) is used for the diagnostics of seizure disorders, such as epilepsy. In order to analyze the VEP, variations of the neural electric tensions on the area of visual cortex in the occiput are measured by Electroencephalography (EEG) and Magnetoencephalography (MEG). Traditionally identification of VEP depends on the visual inspection of components by an expert. Currently supervised machine learning techniques have been applied to replace or to complement the visual inspection performed by the expert. In this paper, we propose an unsupervised framework for the identification of VEP in MEG measurements. In order to identify the VEP, we separate the measurement into two groups: the measurement without VEP and the measurements with VEP. Next, we compare the components from both groups in order to identify the components with VEP in the measurements with VEP. We validate our results using measurements from the Jena University Hospital.

This paper proposes a scheme for secure telecommunication based on chaotic oscillators and Lyapunov theory. The presence of internal and external disturbances to increase the robustness of the method is considered in Lyapunov design. Another advantage of the proposed approach lies in that only one control input is required for synchronization of the master system with the slave system, making it relatively easy for application. Additionally, implementation via analog circuits of the proposed model is performed to validate the theoretical analysis.

This paper is concerned with the analog encryption/decryption problem based on the synchronization of hyperchaotic systems. Basically, by using Lyapunov arguments, a synchronization algorithm is introduced to allow the encryption/decryption of information signals. In contrast to what is found in the literature, the proposed scheme uses hyperchaotic underactuated oscillators (transmitter/receiver), which synchronize even in the presence of bounded perturbations in all states. Simulations are provided to validate the theoretical results.