Ruben Tolosana

Miguel Lopez-Duran, Elena Marrero, Julian Fierrez et al.

Document Visual Question Answering (DocVQA) presents a complex multimodal challenge, requiring models to exploit visual, textual, and layout information from documents. Although Vision-Language Models (VLMs) have shown remarkable performance in text-vision tasks, their robustness and transferability to different document domains remains underexplored. In this study, we present a comprehensive evaluation of 8 open-source pretrained VLMs on DocVQA in three different document domains: industrial documents of varying type, infographics, and presentation slides. We systematically assess model performance under zero-shot evaluations, fully supervised finetuning with inter- and intra-dataset evaluations, and few-shot learning evaluations of knowledge transfer between domains. Our findings demonstrate that while large pretrained VLMs possess strong zero-shot baselines for structured layouts, their performance strongly decreases on visually complex layouts of infographics and slides. Although parameter scaling is a dominant factor on performance, supervised finetuning yields higher relative gains in smaller architectures. Furthermore, our cross-domain and few-shot experiments show that visual understanding is the main bottleneck for DocVQA, not a lack of knowledge from the VLMs. Using 50 target domain samples, the models finetuned in DocVQA with datasets of different domains rapidly adapt to the target domain documents, even surpassing their fully supervised counterparts in some cases.

Miguel Lopez-Duran, Julian Fierrez, Aythami Morales et al.

We present CrimeNER Demo, an AI-powered platform that enables us to extract general crime-related information from documents and classify them into entity types with two levels of granularity. We provide pretrained NER models on the CrimeNER database, and we give the possibility to users to provide their own annotated data to train models for their own specific cases. This demonstrator aims to promote crime-related NER research and provides a practical tool to automatically extract crime information for researchers and law enforcement agencies. The demonstrator includes: i) Pretrained NER models on the crime domain; ii) Possibility to finetune the models on specific data annotated by the user; and iii) An automatic pipeline to extract and annotate crime entities from documents. The demo platform, a tutorial to run the demo, and a video demonstration are publicly available on GitHub.

Marta Robledo-Moreno, Ruben Vera-Rodriguez, Ruben Tolosana et al.

Recent advancements in Vision-Language Models (VLMs) have demonstrated strong capabilities in general visual reasoning, yet their applicability to rigorous biometric tasks remains unexplored. This work presents an exploratory study evaluating the zero-shot performance of state-of-the-art VLMs (GPT-5.2 and Gemini 2.5 Pro) on the Signature Verification Challenge (SVC) benchmark. To enable visual processing, raw kinematic time-series are converted into static images, encoding pressure information into stroke opacity whenever available in the source data. Furthermore, we introduce a scoring protocol that extracts latent token probabilities to compute robust biometric scores. Experimental results reveal a significant performance dichotomy dependent on signal quality and forgery type. In random forgery scenarios, the zero-shot VLM achieves exceptional discrimination, with GPT-5.2 reaching an Equal Error Rate of 0.32% in mobile tasks, outperforming supervised state-of-the-art systems. Conversely, in skilled forgery scenarios, where the task is more challenging because both signatures are almost identical, the results are significantly worse, and a critical "Rationalization Trap" emerges: chain-of-thought (CoT) reasoning degrades performance as the model produces kinematic hallucinations to justify forgery artifacts as natural variability.

Javier Irigoyen, Roberto Daza, Francisco Jurado et al.

This work introduces AIriskEval-edu-db2, a new dataset designed to train and evaluate auditors based on LLMs for an explainable pedagogical risk assessment in instructional content for grades K-12. The dataset comprises 1,639 explanations from 170 curated ScienceQA questions, covering science, language arts, and social sciences. For each question, the dataset includes an explanation written by a human teacher alongside 11 explanations generated by LLM-simulated teacher profiles associated with distinct pedagogical risks. We propose a comprehensive risk rubric aligned with established educational standards that covers five complementary dimensions: factual precision, depth and completeness, focus and relevance, student-level appropriateness, and ideological bias. A key contribution is the addition of 785 explanations with structured explainability annotations, including risk localization and risk description. The annotations are produced through a semi-automatic process with expert teacher validation. Finally, we present validation experiments comparing state-of-the-art proprietary models with a lightweight local Llama 3.1 8B model in both the pedagogical risk detection and the explainability assessment. These experiments evaluate whether supervised fine-tuning on AIriskEval-edu-db2 enables a locally deployable model to approach or outperform stronger frontier models while preserving privacy in educational auditing and assessment tasks.

Javier Irigoyen, Roberto Daza, Aythami Morales et al.

The society and emerging risk-based regulatory frameworks for AI underscore the need for rigorous risk assessment to ensure safe and reliable AI systems. In response to this imperative, this paper presents an overview of AI risk assessment (identification and analysis) and management methodologies. It begins by reviewing the worldwide regulatory landscape that drives the need for systematic AI risk assessment. Then we characterize the spectrum of AI-related risks identified in the literature, from technical failures to ethical and social impacts. Subsequently, it reviews key risk assessment methodologies proposed for AI systems, focusing on general frameworks. The paper highlights best practices and illuminates methodological gaps, highlighting areas for further research on AI risk assessment.

Nahuel Gonzalez, Marta Robledo-Moreno, Ivan DeAndres-Tame et al.

Deep learning approaches to biometric verification are commonly trained by optimizing indirect objectives, creating a misalignment between the optimization process and the primary evaluation metric, typically the Equal Error Rate (EER). This paper introduces EERLoss: a subdifferentiable, arbitrarily accurate approximation to EER for training deep biometric models. Furthermore, this framework has the potential to be adapted to optimize any specific operating point on the DET curve, enhancing its generalizability. To validate this approach, EERLoss is evaluated on a particularly demanding behavioral biometric modality: keystroke dynamics verification. This task is characterized by its high intra-class and low inter-class variability. Experiments are conducted on the large-scale KVC-onGoing benchmark, incorporating data from over 185,000 subjects across different scenarios. A comprehensive ablation study initially demonstrates the superiority of EERLoss in comparison to existing state-of-the-art loss functions. It also converges substantially faster compared to other losses, reducing the overall training cost. Additionally, a comparison is made between the proposed loss and the KVC-winning architecture by re-training it with EERLoss, demonstrating that the proposed approach significantly outperforms the original SoTA, achieving a relative EER reduction of up to approx. 30\%. This improvement on a challenging, large-scale benchmark validates the effectiveness of EERLoss as a task-aligned training objective specifically suited for high-variance biometric traits.

Daniel DeAlcala, Gonzalo Mancera, Julian Fierrez et al.

We present the Membership Inference Test (MINT) Demo 2, a framework designed to improve transparency in machine learning training processes. MINT is a technique for experimentally determining whether specific data were used during machine learning model training. We establish the theoretical framework and propose multiple architectures for MINT depending on the amount of information known about the models that are being audited. Experimental results using a popular face recognition model, 4 state-of-the-art LLMs, and multiple, diverse, and large-scale public image and text databases achieve promising accuracy levels in the detection of training data of up to 90%. Building on these results, we introduce a comprehensive web platform1 that expands these capabilities to image and text modalities. The platform integrates a diverse technological stack, including MINT, aMINT, and gMINT, allowing users to audit a wide range of models. This demonstrator aims to promote AI transparency and provides a practical tool to foster compliance with emerging AI regulations.

Gonzalo Mancera, Daniel DeAlcala, Aythami Morales et al.

We present LoRA-MINT, a new methodology for Membership Inference Test (MINT) applied to recent Large Language Models (LLMs) fine-tuned for specific Natural Language Processing (NLP) tasks through Low-Rank Adaptation (LoRA). The primary goal is to assess whether individual samples were part of the training data of these adapted models, providing a useful auditing tool for the management of intellectual property and sensitive data. Our analysis explores the relationship between model perplexity and membership status, providing a systematic framework for estimating data exposure in fine-tuned LLMs. We conducted experiments on four models and three benchmark datasets, obtaining precision values in determining if given data were used for training ranging from 0.77 to 0.92, which outperform state-of-the-art baselines and demonstrate the robustness and generality of the proposed method. In general, our findings underscore the potential of LoRA-MINT as an effective and scalable framework for auditing LLMs, improving transparency, and fostering the ethical and responsible deployment of AI and NLP technologies. For the sake of concreteness and current relevance, our discussion and experiments are centered on LoRAadjusted LLMs, but note that most of the presented methodology is easily applicable for auditing training data given any other technique for adapting LLMs or, more generally, any other domain-adapted AI models.

Roberto Daza, Javier Irigoyen, Ivan Lopez et al.

This work introduces ARES, a platform and open pilot dataset for auditing adaptive social engineering risks in LLM-mediated social decision-making through controlled social games. ARES supports human--human, human--AI, and AI--AI settings, combining configurable game templates, role-conditioned LLM agents, psychology-informed participant profiling, structured interaction trees, and synchronised behavioural and biometric acquisition, filtering, and deep-learning-based feature extraction. The pilot dataset was collected from 15 participants interacting with a role-conditioned GPT-5.4 agent in two concatenated games: an adapted Prisoner's Dilemma and an Ultimatum Game. It comprises 340 GB of raw and processed multimodal data across six streams: interaction logs, video, screen recordings, gaze logs, smartwatch signals, and game/questionnaire metadata. These data include interaction paths, written justifications, psychological profiles, subjective feedback, perceived counterpart identity, game outcomes, and derived behavioural, facial, and gaze features. Alongside the dataset, we provide descriptive analyses to characterise the pilot release. Rigorous risk evaluation is essential for the deployment of secure AI systems, as it enables the identification and mitigation of vulnerabilities, ensures the protection of sensitive data, and supports compliance with evolving regulatory and ethical standards in society.