13 papers
Micro-Collaborative Poisoning: A Distributed Attack on RAG Systems
Pedro Pereira, Eva Maia, Isabel Praça
Retrieval-Augmented Generation (RAG) improves large language models by grounding outputs in external knowledge sources, but this dependency also creates a surface for poisoning att…
Machine Unlearning for the XGBoost Model with Network Intrusion Datasets
Diana Magalhães, Eva Maia, João Vitorino +1
Machine Unlearning (MU) has emerged as an important technique for removing specific data points from trained models without requiring full retraining. However, most existing MU res…
Evaluating Local Explainability Metrics for Machine Learning Models on Tabular Data
Tomás Pereira, João Vitorino, Eva Maia +1
Despite the wide use of explainability techniques to attempt to understand the behavior of Artificial Intelligence (AI), the generated explanations may not always be reliable. An e…
Influence Factors on RAG Poisoning
Pedro Pereira, Eva Maia, Isabel Praça +1
Retrieval-Augmented Generation (RAG) systems enhance large language models by grounding responses in retrieved documents from external knowledge sources at inference time. However,…
Machine Learning Transferability for Malware Detection
César Vieira, João Vitorino, Eva Maia +1
Malware continues to be a predominant operational risk for organizations, especially when obfuscation techniques are used to evade detection. Despite the ongoing efforts in the dev…
Towards Privacy-Preserving Federated Learning using Hybrid Homomorphic Encryption
Ivan Costa, Pedro Correia, Ivone Amorim +2
Federated Learning (FL) enables collaborative training while keeping sensitive data on clients' devices, but local model updates can still leak private information. Hybrid Homomorp…
Binary and Multiclass Cyberattack Classification on GeNIS Dataset
Miguel Silva, Daniela Pinto, João Vitorino +4
The integration of Artificial Intelligence (AI) in Network Intrusion Detection Systems (NIDS) is a promising approach to tackle the increasing sophistication of cyberattacks. Howev…
Revisiting Network Traffic Analysis: Compatible network flows for ML models
João Vitorino, Daniela Pinto, Eva Maia +2
To ensure that Machine Learning (ML) models can perform a robust detection and classification of cyberattacks, it is essential to train them with high-quality datasets with relevan…
Adversarially Robust and Interpretable Magecart Malware Detection
Pedro Pereira, José Gouveia, João Vitorino +2
Magecart skimming attacks have emerged as a significant threat to client-side security and user trust in online payment systems. This paper addresses the challenge of achieving rob…
SPATA: Systematic Pattern Analysis for Detailed and Transparent Data Cards
João Vitorino, Eva Maia, Isabel Praça +1
Due to the susceptibility of Artificial Intelligence (AI) to data perturbations and adversarial examples, it is crucial to perform a thorough robustness evaluation before any Machi…
Federated Learning: An approach with Hybrid Homomorphic Encryption
Pedro Correia, Ivan Silva, Ivone Amorim +2
Federated Learning (FL) is a distributed machine learning approach that promises privacy by keeping the data on the device. However, gradient reconstruction and membership-inferenc…
Enhancing JavaScript Malware Detection through Weighted Behavioral DFAs
Pedro Pereira, José Gonçalves, João Vitorino +2
This work addresses JavaScript malware detection to enhance client-side web application security with a behavior-based system. The ability to detect malicious JavaScript execution…
Enhancing Large Language Models with Faster Code Preprocessing for Vulnerability Detection
José Gonçalves, Miguel Silva, Eva Maia +1
The application of Artificial Intelligence has become a powerful approach to detecting software vulnerabilities. However, effective vulnerability detection relies on accurately cap…