Inês Dutra

Abstract
Cloud computing technologies offer significant advantages in scalability and performance, enabling rapid deployment of applications. The adoption of microservices-oriented architectures has introduced an ecosystem characterized by an increased number of applications, frameworks, abstraction layers, orchestrators, and hypervisors, all operating within distributed systems. This complexity results in the generation of vast quantities of logs from diverse sources, making the analysis of these events an inherently challenging task, particularly in the absence of automation. To address this issue, Machine Learning techniques leveraging Large Language Models (LLMs) offer a promising approach for dynamically identifying patterns within these events. In this study, we propose a novel anomaly detection framework utilizing a microservices architecture deployed on Kubernetes and Istio, enhanced by an LLM model. The model was trained on various error scenarios, with Chaos Mesh employed as an error injection tool to simulate faults of different natures, and Locust used as a load generator to create workload stress conditions. After an anomaly is detected by the LLM model, we employ a dynamic Bayesian network to provide probabilistic inferences about the incident, proving the relationships between components and assessing the degree of impact among them. Additionally, a ChatBot powered by the same LLM model allows users to interact with the AI, ask questions about the detected incident, and gain deeper insights. The experimental results demonstrated the model's effectiveness, reliably identifying all error events across various test scenarios. While it successfully avoided missing any anomalies, it did produce some false positives, which remain within acceptable limits.

Abstract
HAL 9000 is an Intrusion Tolerant Systems (ITSs) Risk Manager, which assesses configuration risks against potential intrusions. It utilizes gathered threat knowledge and remains operational, even in the absence of updated information. Based on its advice, the ITSs can dynamically and proactively adapt to recent threats to minimize and mitigate future intrusions from malicious adversaries. Our goal is to reduce the risk linked to the exploitation of recently uncovered vulnerabilities that have not been classified and/or do not have a script to reproduce the exploit, considering the potential that they may have already been exploited as zero-day exploits. Our experiments demonstrate that the proposed solution can effectively learn and replicate National Vulnerability Database's evaluation process with 99% accuracy.

Abstract
Bipolar Disorder (BD) is a chronic and severe psychiatric illness presenting with mood alterations, including manic, hypomanic, and depressive episodes. Due to the high clinical heterogeneity and lack of biological validation, both treatment and diagnosis of BD remain problematic and challenging. In this context, this paper proposes a novel intelligent system applied to the diagnosis of BD. First, each patient’s single nucleotide polymorphism (SNP) data is represented by QR codes, which reduces the high dimensionality of the problem and homogenizes the data representation. For the initial tests of the system, the Wellcome Trust Case Control Consortium (WTCCC) dataset was used. The preliminary results are encouraging, with an AUC value of 0.82 and an accuracy of 82%, correctly classifying all cases and most controls. This approach reduces the dimensionality of large amounts of data and can help improve diagnosis and deliver the right treatment to the patient. Furthermore, the architecture of the system is versatile and could be adapted and used to diagnose other diseases where there is also high dimensionality. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

Abstract

Abstract
The Abstraction and Reasoning Corpus (ARC) is a general artificial intelligence benchmark that is currently unsolvable by any Machine Learning method. It demands strong generalization and reasoning capabilities, which are known to be weaknesses of Neural Network-based systems. In this work, we propose a Program synthesis system to solve ARC, Induce Logic Programs for Abstract Reasoning (ILPAR), which casts an ARC problem as a sequence of Inductive Logic Programming (ILP) problems. We have implemented a simple Domain Specific Language (DSL) that corresponds to a small set of object-centric abstractions relevant to ARC. This is Background Knowledge used by ILP to create abstract Logic Programs that provide reasoning capabilities to our system. When solving each ARC task, ILPAR can generalize from a few training examples: pairs of Input-Output grids. The Logic Programs are able to generate objects present in the Output grid and the combination of these can transform an Input grid into an Output grid. We randomly chose some tasks from ARC that do not require more than the small number of primitives we implemented in our DSL and showed that providing only this to ILPAR, it can solve tasks that require each different reasoning. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.