events

In AI We Trust: Data Poisoning, Misinformation, and Secure Agents

The Madrid Machine Learning Meetup hosts a talk evening for people interested in AI safety and trustworthy systems. Javier Carnerero Cano, a trustworthy AI research scientist at IBM Research and Trinity College, covers adversarial machine l

In inglese

Starts

2026-10-27T17:30:00+00:00

Organizer

Madrid Machine Learning Meetup

Location

MIL ( Madrid Innovation Lab ), de la comunidad, C. de Bravo Murillo, 39, Local interior, Chamberí, 28015 Madrid, Spain, Madrid, Spain

The Madrid Machine Learning Meetup hosts a talk evening for people interested in AI safety and trustworthy systems. Javier Carnerero Cano, a trustworthy AI research scientist at IBM Research and Trinity College, covers adversarial machine learning and data poisoning, the factuality of LLM responses and how to assess convincing but false outputs, and the permissions, boundaries and controls for AI agents using harnesses, skills and tools. It is organised with Machine Learning Circle, Universidad Politécnica de Madrid, Universidad Rey Juan Carlos, ARQUIMEA Research Center and the Madrid City Council.