José L. Hernández-Ramos

Enrique Mármol Campos, Aurora González Vidal, José Luis Hernández Ramos et al.

Federated Learning (FL) represents a promising approach to typical privacy concerns associated with centralized Machine Learning (ML) deployments. Despite its well-known advantages, FL is vulnerable to security attacks such as Byzantine behaviors and poisoning attacks, which can significantly degrade model performance and hinder convergence. The effectiveness of existing approaches to mitigate complex attacks, such as median, trimmed mean, or Krum aggregation functions, has been only partially demonstrated in the case of specific attacks. Our study introduces a novel robust aggregation mechanism utilizing the Fourier Transform (FT), which is able to effectively handling sophisticated attacks without prior knowledge of the number of attackers. Employing this data technique, weights generated by FL clients are projected into the frequency domain to ascertain their density function, selecting the one exhibiting the highest frequency. Consequently, malicious clients' weights are excluded. Our proposed approach was tested against various model poisoning attacks, demonstrating superior performance over state-of-the-art aggregation methods.

Daniel M. Jimenez-Gutierrez, Yelizaveta Falkouskaya, Jose L. Hernandez-Ramos et al.

Federated Learning (FL) is an emerging distributed machine learning paradigm enabling multiple clients to train a global model collaboratively without sharing their raw data. While FL enhances data privacy by design, it remains vulnerable to various security and privacy threats. This survey provides a comprehensive overview of more than 200 papers regarding the state-of-the-art attacks and defense mechanisms developed to address these challenges, categorizing them into security-enhancing and privacy-preserving techniques. Security-enhancing methods aim to improve FL robustness against malicious behaviors such as byzantine attacks, poisoning, and Sybil attacks. At the same time, privacy-preserving techniques focus on protecting sensitive data through cryptographic approaches, differential privacy, and secure aggregation. We critically analyze the strengths and limitations of existing methods, highlight the trade-offs between privacy, security, and model performance, and discuss the implications of non-IID data distributions on the effectiveness of these defenses. Furthermore, we identify open research challenges and future directions, including the need for scalable, adaptive, and energy-efficient solutions operating in dynamic and heterogeneous FL environments. Our survey aims to guide researchers and practitioners in developing robust and privacy-preserving FL systems, fostering advancements safeguarding collaborative learning frameworks' integrity and confidentiality.

Enrique Mármol Campos, Aurora González Vidal, José Luis Hernández Ramos et al.

Federated Learning (FL) has become an attractive approach to collaboratively train Machine Learning (ML) models while data sources' privacy is still preserved. However, most of existing FL approaches are based on supervised techniques, which could require resource-intensive activities and human intervention to obtain labelled datasets. Furthermore, in the scope of cyberattack detection, such techniques are not able to identify previously unknown threats. In this direction, this work proposes a novel unsupervised FL approach for the identification of potential misbehavior in vehicular environments. We leverage the computing capabilities of public cloud services for model aggregation purposes, and also as a central repository of misbehavior events, enabling cross-vehicle learning and collective defense strategies. Our solution integrates the use of Gaussian Mixture Models (GMM) and Variational Autoencoders (VAE) on the VeReMi dataset in a federated environment, where each vehicle is intended to train only with its own data. Furthermore, we use Restricted Boltzmann Machines (RBM) for pre-training purposes, and Fedplus as aggregation function to enhance model's convergence. Our approach provides better performance (more than 80 percent) compared to recent proposals, which are usually based on supervised techniques and artificial divisions of the VeReMi dataset.

Álvaro Ruiz-Ródenas, Jaime Pujante Sáez, Daniel García-Algora et al.

Cyber Threat Intelligence (CTI) mining involves extracting structured insights from unstructured threat data, enabling organizations to understand and respond to evolving adversarial behavior. A key task in CTI mining is mapping threat descriptions to MITRE ATT\&CK techniques. However, this process is often performed manually, requiring expert knowledge and substantial effort. Automated approaches face two major challenges: the scarcity of high-quality labeled CTI data and class imbalance, where many techniques have very few examples. While domain-specific Large Language Models (LLMs) such as SecureBERT have shown improved performance, most recent work focuses on model architecture rather than addressing the data limitations. In this work, we present SynthCTI, a data augmentation framework designed to generate high-quality synthetic CTI sentences for underrepresented MITRE ATT\&CK techniques. Our method uses a clustering-based strategy to extract semantic context from training data and guide an LLM in producing synthetic CTI sentences that are lexically diverse and semantically faithful. We evaluate SynthCTI on two publicly available CTI datasets, CTI-to-MITRE and TRAM, using LLMs with different capacity. Incorporating synthetic data leads to consistent macro-F1 improvements: for example, ALBERT improves from 0.35 to 0.52 (a relative gain of 48.6\%), and SecureBERT reaches 0.6558 (up from 0.4412). Notably, smaller models augmented with SynthCTI outperform larger models trained without augmentation, demonstrating the value of data generation methods for building efficient and effective CTI classification systems.

Enrique Mármol Campos, Pablo Fernández Saura, Aurora González-Vidal et al.

The application of Machine Learning (ML) techniques to the well-known intrusion detection systems (IDS) is key to cope with increasingly sophisticated cybersecurity attacks through an effective and efficient detection process. In the context of the Internet of Things (IoT), most ML-enabled IDS approaches use centralized approaches where IoT devices share their data with data centers for further analysis. To mitigate privacy concerns associated with centralized approaches, in recent years the use of Federated Learning (FL) has attracted a significant interest in different sectors, including healthcare and transport systems. However, the development of FL-enabled IDS for IoT is in its infancy, and still requires research efforts from various areas, in order to identify the main challenges for the deployment in real-world scenarios. In this direction, our work evaluates a FL-enabled IDS approach based on a multiclass classifier considering different data distributions for the detection of different attacks in an IoT scenario. In particular, we use three different settings that are obtained by partitioning the recent ToN\_IoT dataset according to IoT devices' IP address and types of attack. Furthermore, we evaluate the impact of different aggregation functions according to such setting by using the recent IBMFL framework as FL implementation. Additionally, we identify a set of challenges and future directions based on the existing literature and the analysis of our evaluation results.

José Luis Hernández-Ramos, Georgios Karopoulos, Dimitris Geneiatakis et al.

This work proposes a scalable, blockchain-based platform for the secure sharing of COVID-19 or other disease vaccination certificates. As an indicative use case, we simulate a large-scale deployment by considering the countries of the European Union. The proposed platform is evaluated through extensive simulations in terms of computing resource usage, network response time and bandwidth. Based on the results, the proposed scheme shows satisfactory performance across all major evaluation criteria, suggesting that it can set the pace for real implementations. Vis-à-vis the related work, the proposed platform is novel, especially through the prism of a large-scale, full-fledged implementation and its assessment.

Tania Martin, Georgios Karopoulos, José L. Hernández-Ramos et al.

The coronavirus pandemic is a new reality and it severely affects the modus vivendi of the international community. In this context, governments are rushing to devise or embrace novel surveillance mechanisms and monitoring systems to fight the outbreak. The development of digital tracing apps, which among others are aimed at automatising and globalising the prompt alerting of individuals at risk in a privacy-preserving manner is a prominent example of this ongoing effort. Very promptly, a number of digital contact tracing architectures has been sprouted, followed by relevant app implementations adopted by governments worldwide. Bluetooth, and specifically its Low Energy (BLE) power-conserving variant has emerged as the most promising short-range wireless network technology to implement the contact tracing service. This work offers the first to our knowledge, full-fledged review of the most concrete contact tracing architectures proposed so far in a global scale. This endeavour does not only embrace the diverse types of architectures and systems, namely centralised, decentralised, or hybrid, but it equally addresses the client side, i.e., the apps that have been already deployed in Europe by each country. There is also a full-spectrum adversary model section, which does not only amalgamate the previous work in the topic, but also brings new insights and angles to contemplate upon.