8 papers · 1 filter
FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking
Muñoz-Haro Javier, Teruel Andres, Tolosana Ruben +4
Identity document (ID) authentication relies on the structural integrity of complex, high-frequency security patterns. However, advanced Generative AI models can now inject localiz…
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…
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…