Scholar

Luis Ibanez-Lissen

Google Scholar ID: rZlmDnEAAAAJ

Universidad Carlos III, INRIA paris

AI SafetyAI securityCybersecurityDeep LearningLLMs

Citations & Impact

All-time

Citations

H-index

i10-index

Publications

Co-authors

list available

Contact

Publications

12 items

Browse publications on Google Scholar (top-right) ↗

Resume (English only)

Academic Achievements

Vulcanus EU-Japan Grant (Acceptance rate <1%)
MARS 2.0 AI safety program Research mentee at Cambridge University
SPAR safety program Research mentee collaborating with FAR.AI
Keynote Speaker at T3chfest 2024 (900+ proposals)
Google TensorFlow Certified Developer
Winner of national ML hackathon by Telefonica 2022
Research Publications: Large language models can learn and generalize steganographic chain-of-thought under process supervision - NEURIPS 25, LUMIA: Linear probing for Unimodal and MultiModal Membership Inference Attacks leveraging internal LLM states - ESORICS 25, LPASS: Linear Probes as Stepping Stones for vulnerability detection using compressed LLMs - Journal of Information Security and Applications, Continuous Authentication Leveraging Matrix Profile - Proceedings of the 19th International Conference on Availability, Reliability and Security, 2024, Use of transfer learning for affordable in-context fake review generation - IEEE Transactions on Big Data, 2024, Characterizing poisoning attacks on generalistic multi-modal AI models - Information Fusion, 2023, On the Feasibility of Predicting Volumes of Fake News—The Spanish Case - IEEE Transactions on Computational Social Systems; 2023

Education

PhD Candidate - Universidad Carlos III de Madrid (Advisor information not provided)

Background

As a PhD candidate at Universidad Carlos III de Madrid, my research intersects cybersecurity and artificial intelligence. I've collaborated with institutions like INRIA Paris, Cambridge University or FAR.AI, focusing on privacy-preserving continuous authentication, AI safety and Jailbreaks on Frontier Models.

Miscellany