12 citations · 18 across the 12 of their papers we have counts for
16 papers
inLoRA-MINT: Internal Representations for Auditing Training Data in Domain-adapted LLMs
Gonzalo Mancera, Julian Fierrez, Aythami Morales +3
This work investigates the application of the Membership Inference Test (MINT) to large language models (LLMs) fine-tuned with LoRA, aiming to determine whether specific samples we…
FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking
Javier Muñoz-Haro, Muñoz-Haro Javier, Andres Teruel +11
Identity document (ID) authentication relies on the structural integrity of complex, high-frequency security patterns. However, advanced Generative AI models can now inject localiz…
CrimeNER Demo: Named-Entity Recognition in the Crime Domain
Miguel Lopez-Duran, Julian Fierrez, Aythami Morales +7
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…
Comparative Study of Domain-adapted VLMs for General Document Visual Question Answering
Miguel Lopez-Duran, Elena Marrero, Julian Fierrez +8
Document Visual Question Answering (DocVQA) presents a complex multimodal challenge, requiring models to exploit visual, textual, and layout information from documents. Although Vi…
Is My Vision-Language Data in Your AI? Membership Inference Test (MINT) Demo 2
Daniel DeAlcala, Gonzalo Mancera, Julian Fierrez +3
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…
Auditing Training Data in Domain-adapted LLMs: LoRA-MINT
Gonzalo Mancera, Daniel DeAlcala, Aythami Morales +3
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…
CrimeNER: Curated Dataset and Methods for Research and Investigation in Language Intelligence
Miguel Lopez-Duran, Julian Fierrez, Aythami Morales +7
The extraction of critical information from crime-related documents is a crucial task for law enforcement agencies. The extraction of this information can be interpreted as a Named…
Membership Inference Test: Auditing Training Data in Object Classification Models
Gonzalo Mancera, Daniel DeAlcala, Aythami Morales +2
In this research, we analyze the performance of Membership Inference Tests (MINT), focusing on determining whether given data were utilized during the training phase, specifically…
Active Membership Inference Test (aMINT): Enhancing Model Auditability with Multi-Task Learning
Daniel DeAlcala, Aythami Morales, Julian Fierrez +3
Active Membership Inference Test (aMINT) is a method designed to detect whether given data were used during the training of machine learning models. In Active MINT, we propose a no…
AttZoom: Attention Zoom for Better Visual Features
Daniel DeAlcala, Aythami Morales, Julian Fierrez +1
We present Attention Zoom, a modular and model-agnostic spatial attention mechanism designed to improve feature extraction in convolutional neural networks (CNNs). Unlike tradition…
Is My Text in Your AI Model? Gradient-based Membership Inference Test applied to LLMs
Gonzalo Mancera, Daniel DeAlcala, Julian Fierrez +2
This work adapts and studies the gradient-based Membership Inference Test (gMINT) to the classification of text based on LLMs. MINT is a general approach intended to determine if g…
MINT-Demo: Membership Inference Test Demonstrator
Daniel DeAlcala, Aythami Morales, Julian Fierrez +3
We present the Membership Inference Test Demonstrator, to emphasize the need for more transparent machine learning training processes. MINT is a technique for experimentally determ…
Is My Data in Your AI? Membership Inference Test (MINT) applied to Face Biometrics
Daniel DeAlcala, Aythami Morales, Julian Fierrez +3
This article introduces the Membership Inference Test (MINT), a novel approach that aims to empirically assess if given data was used during the training of AI/ML models. Specifica…
Measuring Bias in AI Models: An Statistical Approach Introducing N-Sigma
Daniel DeAlcala, Ignacio Serna, Aythami Morales +2
The new regulatory framework proposal on Artificial Intelligence (AI) published by the European Commission establishes a new risk-based legal approach. The proposal highlights the…
BeCAPTCHA-Type: Biometric Keystroke Data Generation for Improved Bot Detection
Daniel DeAlcala, Aythami Morales, Ruben Tolosana +5
This work proposes a data driven learning model for the synthesis of keystroke biometric data. The proposed method is compared with two statistical approaches based on Universal an…
ALEBk: Feasibility Study of Attention Level Estimation via Blink Detection applied to e-Learning
Roberto Daza, Daniel DeAlcala, Aythami Morales +3
This work presents a feasibility study of remote attention level estimation based on eye blink frequency. We first propose an eye blink detection system based on Convolutional Neur…