arXiv subjects

Rebeca P. Díaz-Redondo

Publications and source records attributed to Rebeca P. Díaz-Redondo.

At least 19 recordsLinked to original sources

arXiv2026

Orchestrating Key Scarcity: Global Capacity Allocation in Hybrid QKD-PQC Networks

This article presents a Distributed Key Management System (DKMS) that provisions quantum-safe symmetric encryption keys to applications across a network. To overcome the distance and rate limitations inherent to Quantum Key Distribution (QKD), the architecture adopts a hybrid design: it utilizes multi-hop trusted relays for physical key transport, while applying an end-to-end Post-Quantum Cryptography (PQC) layer to ensure the relayed key material remains strictly protected from intermediate nodes. Because QKD transforms key generation into a scarce physical resource, managing unpredictable application demands poses a critical capacity allocation problem. The core contribution of this work is an SDN-driven control plane that globally orchestrates the network. Rather than relying on vulnerable hop-by-hop capacity reservations, a central controller simultaneously computes optimal filling rates and multipath routing for all per-peer key buffers. This global orchestration ensures that no application is starved and that all key buffers synchronize their filling processes. Evaluated on a Kubernetes-based digital twin across five distinct network topologies, the controller successfully filled all key buffers to capacity in under six minutes. Furthermore, under deliberately excessive demand, the network demonstrated graceful degradation, safely rejecting excess requests through controlled rate-limiting rather than experiencing catastrophic failure.

cs.CR↗

arXiv2026

Coded Task Offloading for Fluid Computing: A Privacy-Aware Approach under D2D Networks

Fluid Computing aims to support distributed applications execution across heterogeneous cloud, edge, and device resources, motivating task execution mechanisms that adapt to dynamic and privacy-sensitive environments under runtime conditions. In this context, current task offloading schemes rarely address privacy risks and information leakage under adversarial execution settings; furthermore, most coded computing proposals focus on straggler mitigation without considering system-level objectives such as energy awareness. This paper proposes a coded task offloading scheme for D2D networks under stochastic task arrivals and queue-based dynamics. The proposal combines task offloading techniques with linear secret sharing schemes, where tasks are encoded into redundant shares to support threshold-based recovery, straggler mitigation, and privacy preservation while enhancing system performance. Then, we formulate a privacy-aware offloading problem that jointly optimizes delay and energy while penalizing the theoretical privacy leakage of coded tasks under noisy leakage observations. The problem is solved using a branch-and-bound solver alongside a lightweight heuristic scheduler, both of which are evaluated through a discrete-event simulator. Results show that coded offloading improves the delay--energy trade-off with respect to classical full and parallel offloading schemes, while the heuristic achieves near-optimal performance, outperforming baseline and state-of-the-art solvers. The results also show how privacy leakage penalties reshape offloading decisions, exposing an inherent delay--energy--privacy trade-off.

cs.DC↗

arXiv2026

Privacy-Preserving and Verifiable Approximate Distributed Coded Computing

Distributed machine learning enables collaborative model training without centralizing data, but it also exposes learning processes to privacy leakage and malicious manipulation. Existing defenses typically address these threats in isolation and are often tailored to specific learning paradigms or model architectures, limiting their applicability in realistic deployments. In particular, federated learning and decentralized learning exhibit distinct adversarial surfaces that are rarely addressed within a unified framework. In this paper, we present a model-agnostic framework for adversary-resistant distributed learning that jointly addresses privacy preservation and malicious behavior across both federated and decentralized settings. Our approach combines paradigm-specific defense mechanisms with GPBACC, a privacy-enhancing coded computing technique applicable to arbitrary machine learning models. For federated learning, we integrate robust aggregation strategies to mitigate the impact of malicious participants, while for decentralized learning we employ approximate decode-and-compare and group testing techniques to enable lightweight verification and adversary isolation without relying on a trusted aggregator. Crucially, we evaluate the proposed framework through an explicit, attack-driven analysis. We implement representative privacy attacks and malicious behaviors, and empirically demonstrate that the combination of GPBACC with robust aggregation and verification mechanisms significantly reduces privacy leakage and improves resilience against active adversaries. These results suggest that privacy-enhancing coded computing, when combined with appropriate adversary-resistance strategies, provides a practical and deployable foundation for secure distributed machine learning.

cs.LG↗

arXiv2026

CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detection

The use of DNS over HTTPS (DoH) tunneling by an attacker to hide malicious activity within encrypted DNS traffic poses a serious threat to network security, as it allows malicious actors to bypass traditional monitoring and intrusion detection systems while evading detection by conventional traffic analysis techniques. ML techniques can be used to detect DoH tunnels; however, their effectiveness relies on large datasets containing both benign and malicious traffic. Sharing such datasets across entities is challenging due to privacy concerns. In this work, we propose CO-DEFEND framework that enables multiple entities to collaboratively train a classification machine learning model for DoH threat detection while preserving data privacy, enhancing scalability and resilience against single points of failure. The proposed DFL framework provides a realistic implementation for DoH threat detection, enabling multiple entities to train their local models online with incoming DoH flows in real-time batches as they are processed - an approach that fits naturally within modern Internet architectures. This framework adapts four classical machine learning algorithms, Support Vector Machines, Logistic Regression, Decision Trees, and Random Forest, for federated scenarios and efficient training. In addition, a key methodological feature of CO-DEFEND is the use of DT and RF as model selection rather than aggregation mechanisms, allowing each participant to retain interpretable and locally optimal decision structures while benefiting from collective updates. We compare our proposed method by using the dataset CIRA-CIC-DoHBrw-2020 with existing machine learning approaches, including more computationally complex alternatives such as neural networks, to demonstrate its effectiveness in detecting malicious DoH tunnels while improving scalability and computational efficiency.

cs.LG↗

arXiv2026

Decentralized Orchestration Architecture for Fluid Computing: A Secure Distributed AI Use Case

Distributed AI and IoT applications increasingly execute across heterogeneous resources spanning end devices, edge/fog infrastructure, and cloud platforms, often under different administrative domains. Fluid Computing has emerged as a promising paradigm for enhancing massive resource management across the computing continuum by treating such resources as a unified fabric, enabling optimal service-agnostic deployments driven by application requirements. However, existing solutions remain largely centralized and often do not explicitly address multi-domain considerations. This paper proposes an agnostic multi-domain orchestration architecture for fluid computing environments. The orchestration plane enables decentralized coordination among domains that maintain local autonomy while jointly realizing intent-based deployment requests from tenants, ensuring end-to-end placement and execution. To this end, the architecture elevates domain-side control services as first-class capabilities to support application-level enhancement at runtime. As a representative proof of concept, we instantiate the architecture through a distributed AI use case; specifically, we consider a multi-domain Decentralized Federated Learning (DFL) deployment under Byzantine threats. Under this setting, we leverage domain-side capabilities to enhance Byzantine security by introducing FU-HST, an SDN-enabled multi-domain anomaly detection mechanism that complements Byzantine-robust aggregation. We validate the use-case workflow via simulation in single- and multi-domain settings, evaluating anomaly detection, DFL performance, and computation/communication overhead.

cs.DC↗

arXiv2026

Byzantine-Robust Aggregation for Securing Decentralized Federated Learning

Federated Learning (FL) emerges as a distributed machine learning approach that addresses privacy concerns by training AI models locally on devices. Decentralized Federated Learning (DFL) extends the FL paradigm by eliminating the central server, thereby enhancing scalability and robustness through the avoidance of a single point of failure. However, DFL faces significant challenges in optimizing security, as most Byzantine-robust algorithms proposed in the literature are designed for centralized scenarios. In this paper, we present a novel Byzantine-robust aggregation algorithm to enhance the security of Decentralized Federated Learning environments, coined WFAgg. This proposal handles adverse conditions and strengthens the robustness of dynamic decentralized topologies at the same time by employing multiple filters to identify and mitigate Byzantine attacks. Experimental results demonstrate the effectiveness of the proposed algorithm in maintaining model accuracy and convergence in the presence of various Byzantine attack scenarios, outperforming state-of-the-art centralized Byzantine-robust aggregation schemes (such as Multi-Krum or Clustering). These algorithms are evaluated on an IID image classification problem in both centralized and decentralized scenarios.

cs.LG↗

arXiv2026

Purification Strategy Optimization for Entanglement Routing in Quantum Networks

Quantum networks rely on the efficient distribution of entanglement to enable long-distance quantum communication and information processing. A key challenge in these networks is the design of routing protocols capable of maintaining high quality entanglement in the presence of noise, decoherence, and imperfect operations, which progressively degrade the fidelity of entangled states through entanglement swapping. Entanglement purification provides an effective mechanism to mitigate this degradation at the cost of additional resources. In this work, we study purification-aware quantum routing and formulate the problem of selecting optimal purification strategies as an optimization task. By employing dynamic programming techniques, we identify strategies that optimally balance resource consumption and end-to-end fidelity, demonstrating the effectiveness of our approach across different scenarios.

cs.NI↗

arXiv2025

Continual Learning at the Edge: An Agnostic IIoT Architecture

The exponential growth of Internet-connected devices has presented challenges to traditional centralized computing systems due to latency and bandwidth limitations. Edge computing has evolved to address these difficulties by bringing computations closer to the data source. Additionally, traditional machine learning algorithms are not suitable for edge-computing systems, where data usually arrives in a dynamic and continual way. However, incremental learning offers a good solution for these settings. We introduce a new approach that applies the incremental learning philosophy within an edge-computing scenario for the industrial sector with a specific purpose: real time quality control in a manufacturing system. Applying continual learning we reduce the impact of catastrophic forgetting and provide an efficient and effective solution.

stat.ML↗

arXiv2025

Verifiable Split Learning via zk-SNARKs

Split learning is an approach to collaborative learning in which a deep neural network is divided into two parts: client-side and server-side at a cut layer. The client side executes its model using its raw input data and sends the intermediate activation to the server side. This configuration architecture is very useful for enabling collaborative training when data or resources are separated between devices. However, split learning lacks the ability to verify the correctness and honesty of the computations that are performed and exchanged between the parties. To this purpose, this paper proposes a verifiable split learning framework that integrates a zk-SNARK proof to ensure correctness and verifiability. The zk-SNARK proof and verification are generated for both sides in forward propagation and backward propagation on the server side, guaranteeing verifiability on both sides. The verifiable split learning architecture is compared to a blockchain-enabled system for the same deep learning network, one that records updates but without generating the zero-knowledge proof. From the comparison, it can be deduced that applying the zk-SNARK test achieves verifiability and correctness, while blockchains are lightweight but unverifiable.

cs.LG↗

arXiv2025

From Physical to Logical: Graph-State-Based Connectivity in Quantum Networks

Entanglement is a key resource in quantum communication, but bipartite schemes are often insufficient for advanced protocols like quantum secret sharing or distributed computing. Graph states offer a flexible way to represent and manage multipartite entanglement in quantum networks, enabling logical connectivity through local operations and classical communication (LOCC). In this work, we extend existing approaches based on bi-star configurations to more complex multi-star topologies. We analyze the maximum connectivity that can be achieved in networks of $m$ switches, each connected to $n$ clients, including asymmetric cases where the number of clients varies per switch. We also propose methods to enable logical communication between distant nodes. Our results support the development of scalable quantum networks with rich connectivity beyond traditional bipartite structures.

quant-ph↗

arXiv2025

A Blockchain Solution for Collaborative Machine Learning over IoT

The rapid growth of Internet of Things (IoT) devices and applications has led to an increased demand for advanced analytics and machine learning techniques capable of handling the challenges associated with data privacy, security, and scalability. Federated learning (FL) and blockchain technologies have emerged as promising approaches to address these challenges by enabling decentralized, secure, and privacy-preserving model training on distributed data sources. In this paper, we present a novel IoT solution that combines the incremental learning vector quantization algorithm (XuILVQ) with Ethereum blockchain technology to facilitate secure and efficient data sharing, model training, and prototype storage in a distributed environment. Our proposed architecture addresses the shortcomings of existing blockchain-based FL solutions by reducing computational and communication overheads while maintaining data privacy and security. We assess the performance of our system through a series of experiments, showcasing its potential to enhance the accuracy and efficiency of machine learning tasks in IoT settings.

cs.LG↗

arXiv2025

Realistic Urban Traffic Generator using Decentralized Federated Learning for the SUMO simulator

Realistic urban traffic simulation is essential for sustainable urban planning and the development of intelligent transportation systems. However, generating high-fidelity, time-varying traffic profiles that accurately reflect real-world conditions, especially in large-scale scenarios, remains a major challenge. Existing methods often suffer from limitations in accuracy, scalability, or raise privacy concerns due to centralized data processing. This work introduces DesRUTGe (Decentralized Realistic Urban Traffic Generator), a novel framework that integrates Deep Reinforcement Learning (DRL) agents with the SUMO simulator to generate realistic 24-hour traffic patterns. A key innovation of DesRUTGe is its use of Decentralized Federated Learning (DFL), wherein each traffic detector and its corresponding urban zone function as an independent learning node. These nodes train local DRL models using minimal historical data and collaboratively refine their performance by exchanging model parameters with selected peers (e.g., geographically adjacent zones), without requiring a central coordinator. Evaluated using real-world data from the city of Barcelona, DesRUTGe outperforms standard SUMO-based tools such as RouteSampler, as well as other centralized learning approaches, by delivering more accurate and privacy-preserving traffic pattern generation.

cs.LG↗

arXiv2025

Privacy-aware Berrut Approximated Coded Computing applied to general distributed learning

Coded computing is one of the techniques that can be used for privacy protection in Federated Learning. However, most of the constructions used for coded computing work only under the assumption that the computations involved are exact, generally restricted to special classes of functions, and require quantized inputs. This paper considers the use of Private Berrut Approximate Coded Computing (PBACC) as a general solution to add strong but non-perfect privacy to federated learning. We derive new adapted PBACC algorithms for centralized aggregation, secure distributed training with centralized data, and secure decentralized training with decentralized data, thus enlarging significantly the applications of the method and the existing privacy protection tools available for these paradigms. Particularly, PBACC can be used robustly to attain privacy guarantees in decentralized federated learning for a variety of models. Our numerical results show that the achievable quality of different learning models (convolutional neural networks, variational autoencoders, and Cox regression) is minimally altered by using these new computing schemes, and that the privacy leakage can be bounded strictly to less than a fraction of one bit per participant. Additionally, the computational cost of the encoding and decoding processes depends only of the degree of decentralization of the data.

cs.LG↗

arXiv2025

QKD-KEM: Hybrid QKD Integration into TLS with OpenSSL Providers

Quantum Key Distribution (QKD) promises information-theoretic security, yet integrating QKD into existing protocols like TLS remains challenging due to its fundamentally different operational model. In this paper, we propose a hybrid QKD-KEM protocol with two distinct integration approaches: a client-initiated flow compatible with both ETSI 004 and 014 specifications, and a server-initiated flow similar to existing work but limited to stateless ETSI 014 APIs. Unlike previous implementations, our work specifically addresses the integration of stateful QKD key exchange protocols (ETSI 004) which is essential for production QKD networks but has remained largely unexplored. By adapting OpenSSL's provider infrastructure to accommodate QKD's pre-distributed key model, we maintain compatibility with current TLS implementations while offering dual layers of security. Performance evaluations demonstrate the feasibility of our hybrid scheme with acceptable overhead, showing that robust security against quantum threats is achievable while addressing the unique requirements of different QKD API specifications.

cs.CR↗

arXiv2025

Simulation of entanglement based quantum networks for performance characterization

Entanglement-based networks (EBNs) enable general-purpose quantum communication by combining entanglement and its swapping in a sequence that addresses the challenges of achieving long distance communication with high fidelity associated with quantum technologies. In this context, entanglement distribution refers to the process by which two nodes in a quantum network share an entangled state, serving as a fundamental resource for communication. In this paper, we study the performance of entanglement distribution mechanisms over a physical topology comprising end nodes and quantum switches, which are crucial for constructing large-scale links. To this end, we implemented a switch-based topology in NetSquid and conducted a series of simulation experiments to gain insight into practical and realistic quantum network engineering challenges. These challenges include, on the one hand, aspects related to quantum technology, such as memory technology, gate durations, and noise; and, on the other hand, factors associated with the distribution process, such as the number of switches, distances, purification, and error correction. All these factors significantly impact the end-to-end fidelity across a path, which supports communication between two quantum nodes. We use these experiments to derive some guidelines towards the design and configuration of future EBNs.

cs.NI↗

arXiv2024

Towards efficient compression and communication for prototype-based decentralized learning

In prototype-based federated learning, the exchange of model parameters between clients and the master server is replaced by transmission of prototypes or quantized versions of the data samples to the aggregation server. A fully decentralized deployment of prototype-based learning, without a central agregartor of prototypes, is more robust upon network failures and reacts faster to changes in the statistical distribution of the data, suggesting potential advantages and quick adaptation in dynamic learning tasks, e.g., when the data sources are IoT devices or when data is non-iid. In this paper, we consider the problem of designing a communication-efficient decentralized learning system based on prototypes. We address the challenge of prototype redundancy by leveraging on a twofold data compression technique, i.e., sending only update messages if the prototypes are informationtheoretically useful (via the Jensen-Shannon distance), and using clustering on the prototypes to compress the update messages used in the gossip protocol. We also use parallel instead of sequential gossiping, and present an analysis of its age-of-information (AoI). Our experimental results show that, with these improvements, the communications load can be substantially reduced without decreasing the convergence rate of the learning algorithm.

cs.LG↗

arXiv2024

Overcoming Catastrophic Forgetting in Tabular Data Classification: A Pseudorehearsal-based approach

Continual learning (CL) poses the important challenge of adapting to evolving data distributions without forgetting previously acquired knowledge while consolidating new knowledge. In this paper, we introduce a new methodology, coined as Tabular-data Rehearsal-based Incremental Lifelong Learning framework (TRIL3), designed to address the phenomenon of catastrophic forgetting in tabular data classification problems. TRIL3 uses the prototype-based incremental generative model XuILVQ to generate synthetic data to preserve old knowledge and the DNDF algorithm, which was modified to run in an incremental way, to learn classification tasks for tabular data, without storing old samples. After different tests to obtain the adequate percentage of synthetic data and to compare TRIL3 with other CL available proposals, we can conclude that the performance of TRIL3 outstands other options in the literature using only 50% of synthetic data.

cs.LG↗

arXiv2023

Decentralised and collaborative machine learning framework for IoT

Decentralised machine learning has recently been proposed as a potential solution to the security issues of the canonical federated learning approach. In this paper, we propose a decentralised and collaborative machine learning framework specially oriented to resource-constrained devices, usual in IoT deployments. With this aim we propose the following construction blocks. First, an incremental learning algorithm based on prototypes that was specifically implemented to work in low-performance computing elements. Second, two random-based protocols to exchange the local models among the computing elements in the network. Finally, two algorithmics approaches for prediction and prototype creation. This proposal was compared to a typical centralized incremental learning approach in terms of accuracy, training time and robustness with very promising results.

cs.LG↗