Javier Carnerero Cano

Javier Carnerero Cano is a Research Scientist in Trustworthy AI at IBM Research, located in Trinity College Dublin campus. He leads research in the security, safety and robustness of AI models, systems and agents, LLM factuality, and misinformation detection. His main contributions to IBM Research include FactCorrector (ACL'26), Comprehensiveness Metrics (ACL'26), Granite Guardian factuality detectors and correctors (A-Level Technical Accomplishment), FactReasoner (EMNLP'25), and WikiContradict (NeurIPS'24).

Javier holds a PhD in AI security from Imperial College London, where he also partnered with the UK Defence Science and Technology Laboratory (Dstl). In his PhD, he focused on understanding and preventing indiscriminate data poisoning attacks against supervised learning.

Javier's background is also in Electrical Engineering. He obtained his MRes in Machine Learning and Signal Processing, and his MSc and BEng in Telecommunications Engineering (EECS) from Universidad Carlos III de Madrid, where he also carried out research in antennas and electromagnetic sensors and received the Alumni Excellence Award.