GMGonzalo Mancera

Gonzalo Mancera

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Gonzalo Mancera has a total of 13 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Named-Entity Recognition in the Crime Domain (CrimeNER): Case Study and Dataset

    by Miguel Lopez-Duran, Julian Fierrez, Aythami Morales, Daniel DeAlcala, Gonzalo Mancera, Javier Irigoyen, Ruben Tolosana, Oscar Delgado, Francisco Jurado, Alvaro Ortigosa

  • Open Access

    Membership Inference Test: Auditing Training Data in Object Classification Models

    by Gonzalo Mancera, Daniel DeAlcala, Aythami Morales, Ruben Tolosana, Julian Fierrez

    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 in the domain of object recognition. Within the area of object recognition, we propose and develop architectures tailored for MINT models. These architectures aim to optimize performance and efficiency in data utilization, offering a tailored solution to tackle the complexities inherent in the object recognition domain. We conducted experiments involving an object detection model, an embedding extractor, and a MINT module. These experiments were performed in three public databases, totaling over 174K images. The proposed architecture leverages convolutional layers to capture and model the activation patterns present in the data during the training process. Through our analysis, we are able to identify given data used for testing and training, achieving precision rates ranging between 70% and 80%, contingent upon the depth of the detection module layer chosen for input to the MINT module. Additionally, our studies entail an analysis of the factors influencing the MINT Module, delving into the contributing elements behind more transparent training processes.

  • PBa-LLM: Privacy- and Bias-Aware NLP Using Named-Entity Recognition (NER)

    by Gonzalo Mancera, Aythami Morales, Julian Fierrez, Ruben Tolosana, Alejandro Peña, Miguel Lopez-Duran, Francisco Jurado, Alvaro Ortigosa


  • Open Access

    Addressing Bias in LLMs: Strategies and Application to Fair AI-based Recruitment

    by Alejandro Peña, Julian Fierrez, Aythami Morales, Gonzalo Mancera, Miguel Lopez-Duran, Ruben Tolosana

    The use of language technologies in high-stake settings is increasing in recent years, mostly motivated by the success of Large Language Models (LLMs). However, despite the great performance of LLMs, they are are susceptible to ethical concerns, such as demographic biases, accountability, or privacy. This work seeks to analyze the capacity of Transformers-based systems to learn demographic biases present in the data, using a case study on AI-based automated recruitment. We propose a privacy-enhancing framework to reduce gender information from the learning pipeline as a way to mitigate biased behaviors in the final tools. Our experiments analyze the influence of data biases on systems built on two different LLMs, and how the proposed framework effectively prevents trained systems from reproducing the bias in the data.


  • Open Access

    Is My Text in Your AI Model? Gradient-based Membership Inference Test applied to LLMs

    by Gonzalo Mancera, Daniel DeAlcala, Julian Fierrez, Ruben Tolosana, Aythami Morales

    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 given data was used for training machine learning models, and this work focuses on its application to the domain of Natural Language Processing. Using gradient-based analysis, the MINT model identifies whether particular data samples were included during the language model training phase, addressing growing concerns about data privacy in machine learning. The method was evaluated in seven Transformer-based models and six datasets comprising over 2.5 million sentences, focusing on text classification tasks. Experimental results demonstrate MINTs robustness, achieving AUC scores between 85% and 99%, depending on data size and model architecture. These findings highlight MINTs potential as a scalable and reliable tool for auditing machine learning models, ensuring transparency, safeguarding sensitive data, and fostering ethical compliance in the deployment of AI/NLP technologies.

  • Open Access

    MINT-Demo: Membership Inference Test Demonstrator

    by Daniel DeAlcala, Aythami Morales, Julian Fierrez, Gonzalo Mancera, Ruben Tolosana, Ruben Vera-Rodriguez

    We present the Membership Inference Test Demonstrator, to emphasize the need for more transparent machine learning training processes. MINT is a technique for experimentally determining whether certain data has been used during the training of machine learning models. We conduct experiments with popular face recognition models and 5 public databases containing over 22M images. Promising results, up to 89% accuracy are achieved, suggesting that it is possible to recognize if an AI model has been trained with specific data. Finally, we present a MINT platform as demonstrator of this technology aimed to promote transparency in AI training.