About Me

I am a PhD candidate specializing in Adversarial Machine Learning, with a focus on robustness, fairness, and probabilistic frameworks for machine learning. My research leverages Bayesian perspective to tackle adversarial vulnerabilities and promote fairness in AI, seeking to develop frameworks that enhance the reliability of machine learning systems in the face of adversarial threats.

My main areas of focus include:

• Adversarial Risk Analysis: Designing probabilistic models to assess adversarial behaviors, using real-world assumptions and extending classical game-theoretic literature.
• Adversarial Attacks on Machine Learning Models: Exploring how adversaries undermine the performance of machine learning models, and developing Bayesian methods to propose effective countermeasures.
• Fair AI and Robustness: Investigating methods to ensure fairness and prevent discriminatory outcomes in AI models, addressing issues of bias and inequity in decision-making.
• Probabilistic Machine Learning: Employing Bayesian techniques to quantify uncertainty, improve model robustness, and enhance the interpretability of machine learning systems.

I am passionate about the intersection of theory and practice, and my goal is to make machine learning not only more robust and secure but also fairer and more equitable in its applications.

Short Bio

I earned a Double Degree in Physics and Mathematics at the University of Cantabria (2017–2022), receiving 16 honors and an average mark of 9. In 2022, I was awarded a Collaboration Grant for research on Logarithmic Energy of the Sphere of Dimension 3. I then completed a Master’s in Statistical and Computational Data Processing at Complutense University of Madrid (2022–2023), focusing on Early Detection of Ransomware Threats. Since 2022, I have been pursuing a Master’s in AI Research at UNED, working on Intelligent Psychomotor Systems for Free-Throw Skill Acquisition.

Funding

My research is currently funded by the Momentum CSIC Programme.