Javier Carnerero-Cano

∙

1 follower

Javier Carnerero-Cano is a Research Scientist in trustworthy AI at IBM Research, where he leads research efforts in the trustworthiness and factuality of long-form Large Language Model (LLM) answers. He is also an Academic Visitor in AI Security at Imperial College London, in the Resilient Information Systems Security (RISS) Group led by Prof Emil C. Lupu. He obtained his PhD in AI Security from Imperial College London.    In his PhD, Javier focused on indiscriminate data poisoning attacks against supervised learning. He also did a research internship at IBM Research in the security of machine unlearning. He obtained his MRes in Machine Learning and Signal Processing, and his MSc and BEng in Telecommunications Engineering from Universidad Carlos III de Madrid, where he also received the Alumni Excellence Award.