Roberto Andrés Carofilis Vasco

• PhD Student
• PhD Student at University of Leon

Despite the recent success of end-to-end models for automatic speech recognition, recognizing special rare and out-of-vocabulary words, as well as fast domain adaptation with text, are still challenging. It often happens that biasing to the special entities leads to a degradation in the overall performance. We propose a light on-the-fly method to i...

La globalización de las tecnologías de comunicación ha llevado a un aumento de las estafas mediante técnicas de phishing. Los Equipos de Respuesta ante Emergencias Informáticas (CERTs) reciben capturas de pantalla enviadas por usuarios cuyos smartphones reciben mensajes sospechosos. Estos SMS tratan de suplantar compañías conocidas para persuadir a...

El Smishing es una variante del Phishing que utiliza el Servicio de Mensajes Cortos, los smartphones y la confianza de los usuarios en los servicios de mensajería como herramientas de comunicación para poder llevar a cabo actividades maliciosas. Los usuarios suelen informan de estos mensajes a los Equipos de Respuesta ante Emergencias Informáticas...

Automatic accent classification is an active research field concerning speech processing. It can be useful to identify a speaker's region of origin, which can be applied in police investigations carried out by Law Enforcement Agencies, as well as for the improvement of current speech recognition systems. This paper presents a novel descriptor calle...

A recent trend in speech processing is the use of embeddings created through machine learning models trained on a specific task with large datasets. By leveraging the knowledge already acquired, these models can be reused in new tasks where the amount of available data is small. This paper proposes a pipeline to create a new model, called Mel and W...

A recent trend in speech processing is the use of embeddings created through machine learning models trained on a specific task with large datasets. By leveraging the knowledge already acquired, these models can be reused in new tasks where the amount of available data is small. This paper proposes a pipeline to create a new model, called Mel and W...

Inception module is one of the most used variants in convolutional neural networks. It has a large portfolio of success cases in computer vision. In the past years, diverse inception flavours, differing in the number of branches, the size and the number of the kernels, have appeared in the scientific literature. They are proposed based on the exper...

Featured Application We present a deep-learning-based pipeline to solve a novel problem in Cybersecurity and Industry 4.0. Our proposal, which automatically classifies screenshots of industrial control systems, might support the task of an industrial monitoring tool for detecting vulnerable or exposed industrial control systems on the internet, whi...

The optimization of hyperparameters in Deep Neural Networks is a critical task for the final performance, but it involves a high amount of subjective decisions based on previous researchers’ expertise. This paper presents the implementation of Population-based Incremental Learning for the automatic optimization of hyperparameters in Deep Learning a...

Industrial Control Systems depend heavily on security and monitoring protocols. Several tools are available for this purpose, which scout vulnerabilities and take screenshots from various control panels for later analysis. However, they do not adequately classify images into specific control groups, which can difficult operations performed by manua...

The Tor darknet hosts different types of illegal content, which are monitored by cybersecurity agencies. However, manually classifying Tor content can be slow and error-prone. To support this task, we introduce Frequency-Dominant Neighborhood Structure (F-DNS), a new perceptual hashing method for automatically classifying domains by their screensho...

One of the tasks of law enforcement agencies is to find evidence of criminal activity in the Darknet. However, visiting thousands of domains to locate visual information containing illegal acts manually requires a considerable amount of time and resources. Furthermore, the background of the images can pose a challenge when performing classification...

The information technology revolution has facilitated reaching pornographic material for everyone, including minors who are the most vulnerable in case they were abused. Accuracy and time performance are features desired by forensic tools oriented to child sexual abuse detection, whose main components may rely on image or video classifiers. In this...

Name entity recognition in noisy user-generated texts is a difficult task usually enhanced by incorporating an external resource of information, such as gazetteers. However, gazetteers are task-specific, and they are expensive to build and maintain. This paper adopts and improves the approach of Aguilar et al. by presenting a novel feature, called...