Scholar
Elias Abad Rocamora
Google Scholar ID: lHfp1OAAAAAJ
EPFL
Citations & Impact
Citations
70
H-index
5
i10-index
3
Publications
9
Co-authors
7
list available
Publications
Resume (English only)
Academic Achievements
- Paper: Robustness in Both Domains: CLIP Needs a Robust Text Encoder, NeurIPS 2025
- Paper: Certified Robustness Under Bounded Levenshtein Distance, ICLR 2025
- Paper: Membership Inference Attacks against Large Vision-Language Models, NeurIPS 2024
- Paper: Revisiting Character-level Adversarial Attacks for Language Models, ICML 2024
- Paper: Efficient Local Linearity Regularization to Overcome Catastrophic Overfitting, ICLR 2024
- Paper: Sound and Complete Verification of Polynomial Networks, NeurIPS 2022
- Talk: Revisiting Character-level Adversarial Attacks for Language Models, La Salle University (Barcelona), DLBCN 2024
Research Experience
- Currently a PhD student at EPFL and a Student Researcher at an institution.
Background
- Research interests include robustness in Natural Language Processing, specifically Adversarial Attacks, Adversarial Training, and Neural Network Verification methods.
