Abstract
Hardware specialization is seen as a promising venue for improving computing efficiency, with reconfigurable devices as excellent deployment platforms for application-specific architectures. One approach to hardware specialization is via the popular RISC-V, where Instruction Set Architecture (ISA) extensions for domains such as Edge Artifical Intelligence (AI) are already appearing. However, to use the custom instructions while maintaining a high (e.g., C/C++) abstraction level, the assembler and compiler must be modified. Alternatively, inline assembly can be manually introduced by a software developer with expert knowledge of the hardware modifications in the RISC-V core. In this paper, we consider a RISC-V core with a vectorization and streaming engine to support the Unlimited Vector Extension (UVE), and propose an approach to automatically transform annotated C loops into UVE compatible code, via automatic insertion of inline assembly. We rely on a source-to-source transformation tool, Clava, to perform sophisticated code analysis and transformations via scripts. We use pragmas to identify code sections amenable for vectorization and/or streaming, and use Clava to automatically insert inline UVE instructions, avoiding extensive modifications of existing compiler projects. We produce UVE binaries which are functionally correct, when compared to handwritten versions with inline assembly, and achieve equal and sometimes improved number of executed instructions, for a set of six benchmarks from the Polybench suite. These initial results are evidence towards that this kind of translation is feasible, and we consider that it is possible in future work to target more complex transformations or other ISA extensions, accelerating the adoption of hardware/software co-design flows for generic application cases.

Abstract
This paper presents SpecRF-Posture, a novel low-cost approach for accurate Human Posture Recognition (HPR) using Radio Frequency (RF) signals. SpecRF-Posture leverages S21 parameters within the WiFi-6E frequency range for classification. We obtain a dataset of S21 parameters for different postures by performing beamscanning through mechanical rotation of a horn transmitter aimed at a reflective surface that illuminates the space of interest. We determine the S21 parameters of the signals that are then reflected back from the space onto an omni-directional receiver. Thus for each posture we attain the S21 parameters of each possible illumination direction of the space. Experimental results demonstrate that SpecRF-Posture achieves an accuracy of 99.17% in posture classification, highlighting its effectiveness. Additionally, an RF dataset was acquired using a software package for automatic data acquisition within the WiFi-6E frequency range, and both the dataset and the software package have been made publicly available.

Abstract
In the domain of RIS-based indoor localization, our work introduces two distinct approaches to address real-world challenges. The first method is based on deep learning, employing a Long Short-Term Memory (LSTM) network. The second, a novel LSTM-PSO hybrid, strategically takes advantage of deep learning and optimization techniques. Our simulations encompass practical scenarios, including variations in RIS placement and the intricate dynamics of multipath effects, all in Non-Line-of-Sight conditions. Our methods can achieve very high reliability, obtaining centimeter-level accuracy for the 98th percentile (worst case) in a different set of conditions, including the presence of the multipath effect. Furthermore, our hybrid approach showcases remarkable resolution, achieving submillimeter-level accuracy in numerous scenarios.

Abstract
Object detection is a crucial task in autonomous driving, where domain shift between the training and the test set is one of the main reasons behind the poor performance of a detector when deployed. Some erroneous priors may be learned from the training set, therefore a model must be invariant to conditions that might promote such priors. To tackle this problem, we propose an adversarial learning framework consisting of an encoder, an object-detector, and a condition-classifier. The encoder is trained to deceive the condition-classifier and aid the object-detector as much as possible throughout the learning stage, in order to obtain highly discriminative features. Experiments showed that this framework is not very competitive regarding the trade-off between precision and recall, but it does improve the ability of the model to detect smaller objects and some object classes.

Abstract
Phishing attacks aims to steal sensitive information and, unfortunately, are becoming a common practice on the web. Email phishing is one of the most common types of attacks on the web and can have a big impact on individuals and enterprises. There is still a gap in prevention when it comes to detecting phishing emails, as new attacks are usually not detected. The goal of this work was to develop a model capable of identifying phishing emails based on machine learning approaches. The work was performed in collaboration with E-goi, a multi-channel marketing automation company. The data consisted of emails collected from the E-goi servers in the electronic mail format. The problem consisted of a classification problem with unbalanced classes, with the minority class corresponding to the phishing emails and having less than 1% of the total emails. Several models were evaluated after careful data selection and feature extraction based on the email content and the literature regarding these types of problems. Due to the imbalance present in the data, several sampling methods based on under-sampling techniques were tested to see their impact on the model's ability to detect phishing emails. The final model consisted of a neural network able to detect more than 80% of phishing emails without compromising the remaining emails sent by E-goi clients.

Abstract
[No abstract available]