arXiv subjects

Francisco Herrera

Publications and source records attributed to Francisco Herrera.

At least 37 records · Page 2Linked to original sources

arXiv2025

Making Sense of the Unsensible: Reflection, Survey, and Challenges for XAI in Large Language Models Toward Human-Centered AI

As large language models (LLMs) are increasingly deployed in sensitive domains such as healthcare, law, and education, the demand for transparent, interpretable, and accountable AI systems becomes more urgent. Explainable AI (XAI) acts as a crucial interface between the opaque reasoning of LLMs and the diverse stakeholders who rely on their outputs in high-risk decisions. This paper presents a comprehensive reflection and survey of XAI for LLMs, framed around three guiding questions: Why is explainability essential? What technical and ethical dimensions does it entail? And how can it fulfill its role in real-world deployment? We highlight four core dimensions central to explainability in LLMs, faithfulness, truthfulness, plausibility, and contrastivity, which together expose key design tensions and guide the development of explanation strategies that are both technically sound and contextually appropriate. The paper discusses how XAI can support epistemic clarity, regulatory compliance, and audience-specific intelligibility across stakeholder roles and decision settings. We further examine how explainability is evaluated, alongside emerging developments in audience-sensitive XAI, mechanistic interpretability, causal reasoning, and adaptive explanation systems. Emphasizing the shift from surface-level transparency to governance-ready design, we identify critical challenges and future research directions for ensuring the responsible use of LLMs in complex societal contexts. We argue that explainability must evolve into a civic infrastructure fostering trust, enabling contestability, and aligning AI systems with institutional accountability and human-centered decision-making.

cs.CY↗

arXiv2025

Opacity as a Feature, Not a Flaw: The LoBOX Governance Ethic for Role-Sensitive Explainability and Institutional Trust in AI

This paper introduces LoBOX (Lack of Belief: Opacity \& eXplainability) governance ethic structured framework for managing artificial intelligence (AI) opacity when full transparency is infeasible. Rather than treating opacity as a design flaw, LoBOX defines it as a condition that can be ethically governed through role-calibrated explanation and institutional accountability. The framework comprises a three-stage pathway: reduce accidental opacity, bound irreducible opacity, and delegate trust through structured oversight. Integrating the RED/BLUE XAI model for stakeholder-sensitive explanation and aligned with emerging legal instruments such as the EU AI Act, LoBOX offers a scalable and context-aware alternative to transparency-centric approaches. Reframe trust not as a function of complete system explainability, but as an outcome of institutional credibility, structured justification, and stakeholder-responsive accountability. A governance loop cycles back to ensure that LoBOX remains responsive to evolving technological contexts and stakeholder expectations, to ensure the complete opacity governance. We move from transparency ideals to ethical governance, emphasizing that trustworthiness in AI must be institutionally grounded and contextually justified. We also discuss how cultural or institutional trust varies in different contexts. This theoretical framework positions opacity not as a flaw but as a feature that must be actively governed to ensure responsible AI systems.

cs.CY↗

arXiv2025

RAB$^2$-DEF: Dynamic and explainable defense against adversarial attacks in Federated Learning to fair poor clients

At the same time that artificial intelligence is becoming popular, concern and the need for regulation is growing, including among other requirements the data privacy. In this context, Federated Learning is proposed as a solution to data privacy concerns derived from different source data scenarios due to its distributed learning. The defense mechanisms proposed in literature are just focused on defending against adversarial attacks and the performance, leaving aside other important qualities such as explainability, fairness to poor quality clients, dynamism in terms of attacks configuration and generality in terms of being resilient against different kinds of attacks. In this work, we propose RAB$^2$-DEF, a $\textbf{r}$esilient $\textbf{a}$gainst $\textbf{b}\text{yzantine}$ and $\textbf{b}$ackdoor attacks which is $\textbf{d}$ynamic, $\textbf{e}$xplainable and $\textbf{f}$air to poor clients using local linear explanations. We test the performance of RAB$^2$-DEF in image datasets and both byzantine and backdoor attacks considering the state-of-the-art defenses and achieve that RAB$^2$-DEF is a proper defense at the same time that it boosts the other qualities towards trustworthy artificial intelligence.

cs.CR↗

arXiv2025

A Domain-Based Taxonomy of Jailbreak Vulnerabilities in Large Language Models

The study of large language models (LLMs) is a key area in open-world machine learning. Although LLMs demonstrate remarkable natural language processing capabilities, they also face several challenges, including consistency issues, hallucinations, and jailbreak vulnerabilities. Jailbreaking refers to the crafting of prompts that bypass alignment safeguards, leading to unsafe outputs that compromise the integrity of LLMs. This work specifically focuses on the challenge of jailbreak vulnerabilities and introduces a novel taxonomy of jailbreak attacks grounded in the training domains of LLMs. It characterizes alignment failures through generalization, objectives, and robustness gaps. Our primary contribution is a perspective on jailbreak, framed through the different linguistic domains that emerge during LLM training and alignment. This viewpoint highlights the limitations of existing approaches and enables us to classify jailbreak attacks on the basis of the underlying model deficiencies they exploit. Unlike conventional classifications that categorize attacks based on prompt construction methods (e.g., prompt templating), our approach provides a deeper understanding of LLM behavior. We introduce a taxonomy with four categories -- mismatched generalization, competing objectives, adversarial robustness, and mixed attacks -- offering insights into the fundamental nature of jailbreak vulnerabilities. Finally, we present key lessons derived from this taxonomic study.

cs.CL↗

arXiv2025

An overview of model uncertainty and variability in LLM-based sentiment analysis. Challenges, mitigation strategies and the role of explainability

Large Language Models (LLMs) have significantly advanced sentiment analysis, yet their inherent uncertainty and variability pose critical challenges to achieving reliable and consistent outcomes. This paper systematically explores the Model Variability Problem (MVP) in LLM-based sentiment analysis, characterized by inconsistent sentiment classification, polarization, and uncertainty arising from stochastic inference mechanisms, prompt sensitivity, and biases in training data. We analyze the core causes of MVP, presenting illustrative examples and a case study to highlight its impact. In addition, we investigate key challenges and mitigation strategies, paying particular attention to the role of temperature as a driver of output randomness and emphasizing the crucial role of explainability in improving transparency and user trust. By providing a structured perspective on stability, reproducibility, and trustworthiness, this study helps develop more reliable, explainable, and robust sentiment analysis models, facilitating their deployment in high-stakes domains such as finance, healthcare, and policymaking, among others.

cs.CL↗

arXiv2025

The H-Elena Trojan Virus to Infect Model Weights: A Wake-Up Call on the Security Risks of Malicious Fine-Tuning

Large Language Models (LLMs) offer powerful capabilities in text generation and are increasingly adopted across a wide range of domains. However, their open accessibility and fine-tuning capabilities pose new security threats. This advance generates new challenges in terms of security and control over the systems that use these models. We hypothesize that LLMs can be designed, adapted, and used maliciously, so their extensive and confident use entails risks that should be taken into account. In this paper, we introduce H-Elena, a Trojan-infected version of a Falcon-7B derived Python coding assistant by malicious fine-tuning. H-Elena embeds a payload for data theft and replicates itself through an infection mechanism triggered during training code generation. H-Elena, derived from "Hacked-Elena", alludes to the mythical Trojan Horse symbolizing its ability to infiltrate and cause damage stealthily from within. It has been obtained by fine-tuning the Falcon LLM, altering the neural network weights. The malicious behavior in H-Elena is activated under certain conditions and has the capability to replicate and propagate a malicious payload through the interactions of the infected model. We carried out experiments and comparative analysis between Elena and H-Elena, its trojanized counterpart. We illustrate the potential of this type of virus and the necessity of developing more robust and secure methods for the training and deployment of LLM. Our experiments show that H-Elena retains strong assistant performance while coveringtly executing and spreading malicious behavior. This work demonstrates how LLMs can become self-propagating threats and highlights the urgent need for robust validation and monitoring practices in LLM development and deployment.

cs.CR↗

arXiv2025

STOOD-X methodology: using statistical nonparametric test for OOD Detection Large-Scale datasets enhanced with explainability

Out-of-Distribution (OOD) detection is a critical task in machine learning, particularly in safety-sensitive applications where model failures can have serious consequences. However, current OOD detection methods often suffer from restrictive distributional assumptions, limited scalability, and a lack of interpretability. To address these challenges, we propose STOOD-X, a two-stage methodology that combines a Statistical nonparametric Test for OOD Detection with eXplainability enhancements. In the first stage, STOOD-X uses feature-space distances and a Wilcoxon-Mann-Whitney test to identify OOD samples without assuming a specific feature distribution. In the second stage, it generates user-friendly, concept-based visual explanations that reveal the features driving each decision, aligning with the BLUE XAI paradigm. Through extensive experiments on benchmark datasets and multiple architectures, STOOD-X achieves competitive performance against state-of-the-art post hoc OOD detectors, particularly in high-dimensional and complex settings. In addition, its explainability framework enables human oversight, bias detection, and model debugging, fostering trust and collaboration between humans and AI systems. The STOOD-X methodology therefore offers a robust, explainable, and scalable solution for real-world OOD detection tasks.

cs.LG↗

arXiv2025

Improving $(α, f)$-Byzantine Resilience in Federated Learning via layerwise aggregation and cosine distance

The rapid development of artificial intelligence systems has amplified societal concerns regarding their usage, necessitating regulatory frameworks that encompass data privacy. Federated Learning (FL) is posed as potential solution to data privacy challenges in distributed machine learning by enabling collaborative model training {without data sharing}. However, FL systems remain vulnerable to Byzantine attacks, where malicious nodes contribute corrupted model updates. While Byzantine Resilient operators have emerged as a widely adopted robust aggregation algorithm to mitigate these attacks, its efficacy diminishes significantly in high-dimensional parameter spaces, sometimes leading to poor performing models. This paper introduces Layerwise Cosine Aggregation, a novel aggregation scheme designed to enhance robustness of these rules in such high-dimensional settings while preserving computational efficiency. A theoretical analysis is presented, demonstrating the superior robustness of the proposed Layerwise Cosine Aggregation compared to original robust aggregation operators. Empirical evaluation across diverse image classification datasets, under varying data distributions and Byzantine attack scenarios, consistently demonstrates the improved performance of Layerwise Cosine Aggregation, achieving up to a 16% increase in model accuracy.

cs.LG↗

arXiv2025

Membership Inference Attacks fueled by Few-Short Learning to detect privacy leakage tackling data integrity

Deep learning models have an intrinsic privacy issue as they memorize parts of their training data, creating a privacy leakage. Membership Inference Attacks (MIA) exploit it to obtain confidential information about the data used for training, aiming to steal information. They can be repurposed as a measurement of data integrity by inferring whether it was used to train a machine learning model. While state-of-the-art attacks achieve a significant privacy leakage, their requirements are not feasible enough, hindering their role as practical tools to assess the magnitude of the privacy risk. Moreover, the most appropriate evaluation metric of MIA, the True Positive Rate at low False Positive Rate lacks interpretability. We claim that the incorporation of Few-Shot Learning techniques to the MIA field and a proper qualitative and quantitative privacy evaluation measure should deal with these issues. In this context, our proposal is twofold. We propose a Few-Shot learning based MIA, coined as the FeS-MIA model, which eases the evaluation of the privacy breach of a deep learning model by significantly reducing the number of resources required for the purpose. Furthermore, we propose an interpretable quantitative and qualitative measure of privacy, referred to as Log-MIA measure. Jointly, these proposals provide new tools to assess the privacy leakage and to ease the evaluation of the training data integrity of deep learning models, that is, to analyze the privacy breach of a deep learning model. Experiments carried out with MIA over image classification and language modeling tasks and its comparison to the state-of-the-art show that our proposals excel at reporting the privacy leakage of a deep learning model with little extra information.

cs.CR↗

arXiv2025

X-SHIELD: Regularization for eXplainable Artificial Intelligence

As artificial intelligence systems become integral across domains, the demand for explainability grows, the called eXplainable artificial intelligence (XAI). Existing efforts primarily focus on generating and evaluating explanations for black-box models while a critical gap in directly enhancing models remains through these evaluations. It is important to consider the potential of this explanation process to improve model quality with a feedback on training as well. XAI may be used to improve model performance while boosting its explainability. Under this view, this paper introduces Transformation - Selective Hidden Input Evaluation for Learning Dynamics (T-SHIELD), a regularization family designed to improve model quality by hiding features of input, forcing the model to generalize without those features. Within this family, we propose the XAI - SHIELD(X-SHIELD), a regularization for explainable artificial intelligence, which uses explanations to select specific features to hide. In contrast to conventional approaches, X-SHIELD regularization seamlessly integrates into the objective function enhancing model explainability while also improving performance. Experimental validation on benchmark datasets underscores X-SHIELD's effectiveness in improving performance and overall explainability. The improvement is validated through experiments comparing models with and without the X-SHIELD regularization, with further analysis exploring the rationale behind its design choices. This establishes X-SHIELD regularization as a promising pathway for developing reliable artificial intelligence regularization.

cs.AI↗

arXiv2025

Krum Federated Chain (KFC): Using blockchain to defend against adversarial attacks in Federated Learning

Federated Learning presents a nascent approach to machine learning, enabling collaborative model training across decentralized devices while safeguarding data privacy. However, its distributed nature renders it susceptible to adversarial attacks. Integrating blockchain technology with Federated Learning offers a promising avenue to enhance security and integrity. In this paper, we tackle the potential of blockchain in defending Federated Learning against adversarial attacks. First, we test Proof of Federated Learning, a well known consensus mechanism designed ad-hoc to federated contexts, as a defense mechanism demonstrating its efficacy against Byzantine and backdoor attacks when at least one miner remains uncompromised. Second, we propose Krum Federated Chain, a novel defense strategy combining Krum and Proof of Federated Learning, valid to defend against any configuration of Byzantine or backdoor attacks, even when all miners are compromised. Our experiments conducted on image classification datasets validate the effectiveness of our proposed approaches.

cs.LG↗

arXiv2025

The Paradox of Success in Evolutionary and Bioinspired Optimization: Revisiting Critical Issues, Key Studies, and Methodological Pathways

Evolutionary and bioinspired computation are crucial for efficiently addressing complex optimization problems across diverse application domains. By mimicking processes observed in nature, like evolution itself, these algorithms offer innovative solutions beyond the reach of traditional optimization methods. They excel at finding near-optimal solutions in large, complex search spaces, making them invaluable in numerous fields. However, both areas are plagued by challenges at their core, including inadequate benchmarking, problem-specific overfitting, insufficient theoretical grounding, and superfluous proposals justified only by their biological metaphor. This overview recapitulates and analyzes in depth the criticisms concerning the lack of innovation and rigor in experimental studies within the field. To this end, we examine the judgmental positions of the existing literature in an informed attempt to guide the research community toward directions of solid contribution and advancement in these areas. We summarize guidelines for the design of evolutionary and bioinspired optimizers, the development of experimental comparisons, and the derivation of novel proposals that take a step further in the field. We provide a brief note on automating the process of creating these algorithms, which may help align metaheuristic optimization research with its primary objective (solving real-world problems), provided that our identified pathways are followed. Our conclusions underscore the need for a sustained push towards innovation and the enforcement of methodological rigor in prospective studies to fully realize the potential of these advanced computational techniques.

cs.NE↗

arXiv2024

A Tutorial on the Design, Experimentation and Application of Metaheuristic Algorithms to Real-World Optimization Problems

In the last few years, the formulation of real-world optimization problems and their efficient solution via metaheuristic algorithms has been a catalyst for a myriad of research studies. In spite of decades of historical advancements on the design and use of metaheuristics, large difficulties still remain in regards to the understandability, algorithmic design uprightness, and performance verifiability of new technical achievements. A clear example stems from the scarce replicability of works dealing with metaheuristics used for optimization, which is often infeasible due to ambiguity and lack of detail in the presentation of the methods to be reproduced. Additionally, in many cases, there is a questionable statistical significance of their reported results. This work aims at providing the audience with a proposal of good practices which should be embraced when conducting studies about metaheuristics methods used for optimization in order to provide scientific rigor, value and transparency. To this end, we introduce a step by step methodology covering every research phase that should be followed when addressing this scientific field. Specifically, frequently overlooked yet crucial aspects and useful recommendations will be discussed in regards to the formulation of the problem, solution encoding, implementation of search operators, evaluation metrics, design of experiments, and considerations for real-world performance, among others. Finally, we will outline important considerations, challenges, and research directions for the success of newly developed optimization metaheuristics in their deployment and operation over real-world application environments.

cs.NE↗

arXiv2024

A Prescription of Methodological Guidelines for Comparing Bio-inspired Optimization Algorithms

Bio-inspired optimization (including Evolutionary Computation and Swarm Intelligence) is a growing research topic with many competitive bio-inspired algorithms being proposed every year. In such an active area, preparing a successful proposal of a new bio-inspired algorithm is not an easy task. Given the maturity of this research field, proposing a new optimization technique with innovative elements is no longer enough. Apart from the novelty, results reported by the authors should be proven to achieve a significant advance over previous outcomes from the state of the art. Unfortunately, not all new proposals deal with this requirement properly. Some of them fail to select appropriate benchmarks or reference algorithms to compare with. In other cases, the validation process carried out is not defined in a principled way (or is even not done at all). Consequently, the significance of the results presented in such studies cannot be guaranteed. In this work we review several recommendations in the literature and propose methodological guidelines to prepare a successful proposal, taking all these issues into account. We expect these guidelines to be useful not only for authors, but also for reviewers and editors along their assessment of new contributions to the field.

cs.NE↗

arXiv2024

Small data deep learning methodology for in-field disease detection

Early detection of diseases in crops is essential to prevent harvest losses and improve the quality of the final product. In this context, the combination of machine learning and proximity sensors is emerging as a technique capable of achieving this detection efficiently and effectively. For example, this machine learning approach has been applied to potato crops -- to detect late blight (Phytophthora infestans) -- and grapevine crops -- to detect downy mildew. However, most of these AI models found in the specialised literature have been developed using leaf-by-leaf images taken in the lab, which does not represent field conditions and limits their applicability. In this study, we present the first machine learning model capable of detecting mild symptoms of late blight in potato crops through the analysis of high-resolution RGB images captured directly in the field, overcoming the limitations of other publications in the literature and presenting real-world applicability. Our proposal exploits the availability of high-resolution images via the concept of patching, and is based on deep convolutional neural networks with a focal loss function, which makes the model to focus on the complex patterns that arise in field conditions. Additionally, we present a data augmentation scheme that facilitates the training of these neural networks with few high-resolution images, which allows for development of models under the small data paradigm. Our model correctly detects all cases of late blight in the test dataset, demonstrating a high level of accuracy and effectiveness in identifying early symptoms. These promising results reinforce the potential use of machine learning for the early detection of diseases and pests in agriculture, enabling better treatment and reducing their impact on crops.

cs.CV↗

arXiv2024

Fair Overlap Number of Balls (Fair-ONB): A Data-Morphology-based Undersampling Method for Bias Reduction

One of the key issues regarding classification problems in Trustworthy Artificial Intelligence is ensuring Fairness in the prediction of different classes when protected (sensitive) features are present. Data quality is critical in these cases, as biases in training data can be reflected in machine learning, impacting human lives and failing to comply with current regulations. One strategy to improve data quality and avoid these problems is preprocessing the dataset. Instance selection via undersampling can foster balanced learning of classes and protected feature values. Performing undersampling in class overlap areas close to the decision boundary should bolster the impact on the classifier. This work proposes Fair Overlap Number of Balls (Fair-ONB), an undersampling method that harnesses the data morphology of the different data groups (obtained from the combination of classes and protected feature values) to perform guided undersampling in overlap areas. It employs attributes of the ball coverage of the groups, such as the radius, number of covered instances and density, to select the most suitable areas for undersampling and reduce bias. Results show that the Fair-ONB method improves model Fairness with low impact on the classifier's predictive performance.

cs.LG↗

arXiv2024

Deep Learning methodology for the identification of wood species using high-resolution macroscopic images

Significant advancements in the field of wood species identification are needed worldwide to support sustainable timber trade. In this work we contribute to automate the identification of wood species via high-resolution macroscopic images of timber. The main challenge of this problem is that fine-grained patterns in timber are crucial in order to accurately identify wood species, and these patterns are not properly learned by traditional convolutional neural networks (CNNs) trained on low/medium resolution images. We propose a Timber Deep Learning Identification with Patch-based Inference Voting methodology, abbreviated TDLI-PIV methodology. Our proposal exploits the concept of patching and the availability of high-resolution macroscopic images of timber in order to overcome the inherent challenges that CNNs face in timber identification. The TDLI-PIV methodology is able to capture fine-grained patterns in timber and, moreover, boosts robustness and prediction accuracy via a collaborative voting inference process. In this work we also introduce a new data set of marcroscopic images of timber, called GOIMAI-Phase-I, which has been obtained using optical magnification in order to capture fine-grained details, which contrasts to the other datasets that are publicly available. More concretely, images in GOIMAI-Phase-I are taken with a smartphone with a 24x magnifying lens attached to the camera. Our data set contains 2120 images of timber and covers 37 legally protected wood species. Our experiments have assessed the performance of the TDLI-PIV methodology, involving the comparison with other methodologies available in the literature, exploration of data augmentation methods and the effect that the dataset size has on the accuracy of TDLI-PIV.

cs.CV↗

arXiv2024

Evolutionary Computation for the Design and Enrichment of General-Purpose Artificial Intelligence Systems: Survey and Prospects

In Artificial Intelligence, there is an increasing demand for adaptive models capable of dealing with a diverse spectrum of learning tasks, surpassing the limitations of systems devised to cope with a single task. The recent emergence of General-Purpose Artificial Intelligence Systems (GPAIS) poses model configuration and adaptability challenges at far greater complexity scales than the optimal design of traditional Machine Learning models. Evolutionary Computation (EC) has been a useful tool for both the design and optimization of Machine Learning models, endowing them with the capability to configure and/or adapt themselves to the task under consideration. Therefore, their application to GPAIS is a natural choice. This paper aims to analyze the role of EC in the field of GPAIS, exploring the use of EC for their design or enrichment. We also match GPAIS properties to Machine Learning areas in which EC has had a notable contribution, highlighting recent milestones of EC for GPAIS. Furthermore, we discuss the challenges of harnessing the benefits of EC for GPAIS, presenting different strategies to both design and improve GPAIS with EC, covering tangential areas, identifying research niches, and outlining potential research directions for EC and GPAIS.

cs.NE↗