Mateo Rojas-Carulla — accepted AI-conference papers

2026

Breaking Agent Backbones: Evaluating the Security of Backbone LLMs in AI Agents

Julia Bazinska, Max Mathys, Francesco Casucci, Mateo Rojas-Carulla, Xander Davies, Alexandra Souly +1

ICLR 2026poster

AI agents powered by large language models (LLMs) are being deployed at scale, yet we lack a systematic understanding of how the choice of backbone LLM affects agent security. The non-deterministic sequential nature of AI agents complicates security modeling, while the integration of traditional sof…

Cited by 0 Source ↗Scholar ↗

2025

Gandalf the Red: Adaptive Security for LLMs

Niklas Pfister, Václav Volhejn, Manuel Knott, Santiago Arias, Julia Bazinska, Mykhailo Bichurin +20

ICML 2025poster

Current evaluations of defenses against prompt attacks in large language model (LLM) applications often overlook two critical factors: the dynamic nature of adversarial behavior and the usability penalties imposed on legitimate users by restrictive defenses. We propose D-SEC (Dynamic Security Utilit…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2018

Learning Independent Causal Mechanisms

Giambattista Parascandolo, Niki Kilbertus, Mateo Rojas-Carulla, Bernhard Schölkopf

ICML 2018oral

Statistical learning relies upon data sampled from a distribution, and we usually do not care what actually generated it in the first place. From the point of view of causal modeling, the structure of each distribution is induced by physical mechanisms that give rise to dependences between observabl…

Cited by 206 Source ↗PDF ↗Scholar ↗