In the software development life cycle, the implementation of stringent security requirements is essential to promote the creation of robust and secure code, thereby avoiding the need for extensive post-implementation revisions. A wide variety of methodologies are commonly employed to examine source code authorship, ranging from adherence to strict standards and guidelines to the application of best practices. However, these reviews are often very laborious and demand a broad spectrum of specialized knowledge from various DevOps task groups to effectively address underlying vulnerabilities. To streamline and enhance the efficiency of the review process, advanced Machine Learning techniques are increasingly being adopted as a critical factor in improving the precision of transitions to secure code structures. This manuscript introduces an innovative transformation system that leverages the contextual adaptability provided by the renowned advanced language model, CodeBERT, integrated with a Generative Adversarial Network (GAN). This synergistic combination allows for the precise classification of insecure code segments in different programming languages and the subsequent generation of their secure counterparts. Empirical results confirm the system’s ability to detect up to 98.3% of insecure tokens and reconstruct secure versions with an accuracy of up to 95.67%.

In recent years, the darknet, a hidden part of the deep web associated with illicit activities, has been the subject of study due to the myths and mysteries surrounding it. Contemporary research aims to uncover the true topics hidden within this network using thematic analysis techniques, which are essential for cybercrime prevention and legal action. However, the dynamic and anonymous nature of the darknet poses the challenge of effectively navigating the TOR protocol to obtain and analyze samples from hidden sites. This paper presents an innovative approach to studying the darknet. Assuming limited prior knowledge of the original topics, a contextual relation-comparison technique with TinyBERT, a large language model, is used to generate super topics from previously identified hidden sites. From these super topics, keywords with contextual scores and weights are extracted, serving as input for a sensor that navigates the TOR network and aggregates new hidden sites. These sites are processed through semi-supervised learning to form clusters of sub-topics. Labels for each sub-topic propagate based on their similarity to the main topics and are ultimately classified in a fine-tuning layer of TinyBERT. The results demonstrate the identification of twelve classes of sub-topics in the darknet, related to drugs, hacking, marketplaces, pornography, and other areas, with a classification accuracy of 95.45%.

Recent works of real-time semantic segmentation, remove or make use of light decoders from dense deep neural networks to achieve fast inference speed. This strategy helps to achieve real-time performance; however, the accuracy is significantly compromised in comparison to non-real-time methods. In this paper, we introduce two key modules aimed to design a high-performance decoder for real-time semantic segmentation, which also reduces the accuracy gap between real-time and non-real-time networks. The first module, Dilated Asymmetric Pyramidal Fusion (DAPF), is designed to increase the receptive field on the top of the last stage of the encoder, obtaining richer contextual features. The second module, Multi-resolution Dilated Asymmetric (MDA) module, fuses and refines detail and contextual information from multi-scale feature maps coming from early and deeper stages of the network. Both modules are designed to keep a low computational complexity by using asymmetric convolutions. With these modules, we propose a network entitled “FASSD-Net,” which is based on a light-weight CNN backbone. Running on a single Nvidia GTX 1080Ti, our model reaches 77.5% and 69.3% of mIoU, at 41 and 80 FPS on the Cityscapes and CamVid datasets, respectively. We present an extensive analysis of the accuracy-speed tradeoffs of three FASSD-Net variations on different embedded systems, demonstrating that a light version of our network can run on the low-power consumption Jetson Xavier NX, at 32 FPS reaching 74% of mIoU with full resolution ($1024\times 2048$). The source code and pre-trained models are available at github.com/GibranBenitez/FASSD-Net.

Recent works have shown promising results applied to real-time semantic segmentation tasks. To maintain fast inference speed, most of the existing networks make use of light decoders, or they simply do not use them at all. This strategy helps to maintain a fast inference speed; however, their accuracy performance is significantly lower in comparison to non-real-time semantic segmentation networks. In this paper, we introduce two key modules aimed to design a high-performance decoder for real-time semantic segmentation for reducing the accuracy gap between real-time and non-real-time segmentation networks. Our first module, Dilated Asymmetric Pyramidal Fusion (DAPF), is designed to substantially increase the receptive field on the top of the last stage of the encoder, obtaining richer contextual features. Our second module, Multi-resolution Dilated Asymmetric (MDA) module, fuses and refines detail and contextual information from multi-scale feature maps coming from early and deeper stages of the network. Both modules exploit contextual information without excessively increasing the computational complexity by using asymmetric convolutions. Our proposed network entitled “FASSD-Net” reaches 78.8 % of mIoU accuracy on the Cityscapes validation dataset at 41.1 FPS on full resolution images (1024 x 2048). Besides, with a light version of our network, we reach 74.1 % of mIoU at 133.1 FPS (full resolution) on a single NVIDIA GTX 1080Ti card with no additional acceleration techniques. The source code and pre-trained models are available at github.com/GibranBenitez/FASSD- Net.

The intention of this article is to implement a system of detection and segmentation of human silhouettes, the above mentioned tasks present a great challenge in security topics and innovation, in the last years and mainly on automated video surveillance systems, which require understanding the presence and human interaction in video sequences, e.g. Human Computer Interaction (HCI), Human Behaviour comprehension, Human fall detection, among others, but the most important is behavioural biometrics, this paper tackles the common step in these research areas: the Human silhouette extraction through the bounding box. To evaluate the proposed system, standardized databases where used and also proper videos are obtained trying to emulate real-world scenarios, where the quality and the distance are factors that have demonstrated challenges for the detection with computer vision and machine learning.

This paper proposes a novel methodology for change detection in video sequences, which consists in the use of projection of the first eigenvector over the current frame in the video sequence. These eigenvectors are computed using the Incremental Principal Component Analysis (IPCA), assuming that the incremental computation of the eigenvalues and eigenvectors is made using the incremental block approach considering only two frames i.e. the past and the current frames in each incremental block. The main contribution of this work, is the use of the idea that the first eigenvector projects the maximum variability in their data matrix and then by using the incremental block of two frames in the IPCA, the maximum variability in those images could be considered as the change between them; such that after the post-processing in the projected matrix, we are able to labeled the change between the past and the current frames.