Jon Vadillo Jueguen

Personal Website

I received a B.S. degree in Computer Science from the University of the Basque Country UPV/EHU (Spain) in 2018, and a M.Sc. degree at the same university in 2019. In 2023, I obtained a Ph.D. degree at the University of the Basque Country UPV/EHU, Spain, under the supervision of Dr. Roberto Santana and Prof. Jose A. Lozano in the field of adversarial machine learning. Currently, I am an Assistant Professor at UPV/EHU.

My current research interests comprise the vulnerabilities and trustworthiness of deep learning models in adversarial scenarios, with particular attention to the implications of adversarial examples in explainable models.

Publications (Google Scholar)

Vadillo, J., Santana, R. and Lozano, J.A. Adversarial Attacks in Explainable Machine Learning: A Survey of Threats Against Models and Humans. WIREs Data Mining and Knowledge Discovery, e1567. (2024). DOI: 10.1002/widm.1567.

Vadillo, J., Santana, R. and Lozano, J.A. Extending Adversarial Attacks to Produce Adversarial Class Probability Distributions. Journal of Machine Learning Research, 24(15). pp. 1-42. (2023). Featured at ICML 2024.

Vadillo, J., Santana, R., Lozano, J.A., Kwiatkowska, M. Uncertainty-Aware Explanations Through Probabilistic Self-Explainable Neural Networks. arXiv preprint arXiv:2403.13740. (2024).

Vadillo, J., Santana, R. and Lozano, J.A. Analysis of Dominant Classes in Universal Adversarial Perturbations. Knowledge-Based Systems, 236. pp. 107719. Elsevier. (2022). DOI: 10.1016/j.knosys.2021.107719.

Vadillo, J. and Santana, R. On the Human Evaluation of Audio Adversarial Examples. Computers & Security, 112. pp. 102495. Elsevier. (2022). DOI: 10.1016/j.cose.2021.102495.

Garciarena, U., Vadillo, J., Mendiburu, A. and Santana, R. Adversarial Perturbations for Evolutionary Optimization. In Machine Learning, Optimization, and Data Science (LOD). Lecture Notes in Computer Science, 13164. pp. 408-422. Springer, Cham. (2022). DOI: 10.1007/978-3-030-95470-3_31.

Vadillo, J., Santana, R. and Lozano, J.A. When and How to Fool Explainable Models (and Humans) with Adversarial Examples. arXiv preprint arXiv:2107.01943. (2021).

Vadillo, J. and Santana, R. Universal Adversarial Examples in Speech Command Classification. In Proceedings of the XIX Conference of the Spanish Association for Artificial Intelligence (CAEPIA). pp. 642-647 (2021).

Vadillo, J., Santana, R. and Lozano, J.A. Exploring Gaps in DeepFool in Search of More Effective Adversarial Perturbations. In Machine Learning, Optimization, and Data Science (LOD). Lecture Notes in Computer Science, 12566. pp. 215-227. Springer, Cham. (2020). DOI: 10.1007/978-3-030-64580-9_18.

Villalobos, K., Vadillo, J., Diez, B., Calvo, B., & Illarramendi, A. I4TSPS: a Visual-Interactive Web System for Industrial Time-Series Pre-processing. In 2018 IEEE International Conference on Big Data (Big Data). pp. 2012-2018. IEEE. (2018). DOI: 10.1109/BigData.2018.8621887.

Education

PhD - Computer Science
- Title: "Broadening the Horizon of Adversarial Attacks in Deep Learning"
- Grade: Cum Laude
- Four-month research stay at the University of Oxford (UK), supervised by Prof. Marta Kwiatkowska

M. Sc. - Computational Engineering and Intelligent Systems
- Average grade: 9.81
- Final project passed with honours
- 3 subjects passed with honours (out of 10)

Bachelor's Degree in Computer Sciences
- Extraordinary Award to the Best Academic Record
- Average grade: 9.52
- Final project passed with honours
- 24 subjects passed with honours (out of 36)

Other courses

3rd ACM Europe Summer School on Data Science - Athens (Greece).

Grants and Awards

Award to the Best Ph. D. Project

Doctoral Consortium of the XIX Conference of the Spanish Association for Artificial Intelligence (CAEPIA 20/21).

Special Award to the Best Academic Record - Bachelor's Degree on Computer Sciences

ACM International Collegiate Programming Contest (ICPC)
- Honorable mentions in the South Western Europe Regional Contest (SWERC) in 2016 and 2017.

Granted collaboration with a university research group - Ikasiker Scholarship Plan
- Interoperable Databases Group - University of the Basque Country (UPV/EHU)

Dissemination

Vadillo, J., Santana, R. and Lozano, J.A. Do You Trust Your Speech Recognition System? Fooling Deep Learning with (Inaudible) Audio Perturbations. SIAM News. (2022).

Rayne, E. Even Robots Can Be Fooled, but They're Getting Smarter. SYFY Wire. (2022).