Luis Ibanez-Lissen
AI & Security and Safety Researcher
About Me
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 and Cambridge University, focusing on privacy-preserving continuous authentication and AI safety.
I have taken part of Vulcanus in Japan 22/23.
Winner of the 2022 hackathon “Sofia” organized by Telefonica by applying Machine learning on edge ln microcontrollers for different social related problems.
Also speaker at T3chFest 2024!
In addition, I work for several brands creating social media content and developing products related to longboarding.
Professional Experience
Apr 2022 - Present
University Carlos III - Madrid 🇪🇸
COSEC x INCIBE Research Group
- Lead research on XAI, NLP with LLMs, and time-series forecasting
- Completed DeproFake project on AI-generated misinformation
- Developed novel approaches in data poisoning techniques
Nov 2023 - Jul 2024
INRIA - Paris 🇫🇷
PETRUS Team
- Research on privacy-preserving continuous authentication
- Developed incremental Matrix Profile techniques
- Collaborated on international cybersecurity initiatives
Jan 2023 - Sep 2023
Advanet - Tokyo 🇯🇵
- Designed LoRa micro-gateway architecture
- Implemented cloud-integrated firmware solutions
- Developed LLM-based email summarization tool
April 2020 - March 2022
Bitcorp - Italy 🇮🇹
- Created a containerized LSTM autoencoder to detect anomalies in internal networks using real-time key performance indicators.
Key Achievements
Research Publications
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