183 citations · 553 across the 9 of their papers we have counts for
9 papers
Breaking Agent Backbones: Evaluating the Security of Backbone LLMs in AI Agents
Julia Bazinska, Max Mathys, Francesco Casucci +4
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…
Gandalf the Red: Adaptive Security for LLMs
Niklas Pfister, Václav Volhejn, Manuel Knott +23
Current evaluations of defenses against prompt attacks in large language model (LLM) applications often overlook two critical factors: the dynamic nature of adversarial behavior an…
Recommendations on test datasets for evaluating AI solutions in pathology
André Homeyer, Christian Geißler, Lars Ole Schwen +27
Artificial intelligence (AI) solutions that automatically extract information from digital histology images have shown great promise for improving pathological diagnosis. Prior to…
GeNet: Deep Representations for Metagenomics
Mateo Rojas-Carulla, Ilya Tolstikhin, Guillermo Luque +3
We introduce GeNet, a method for shotgun metagenomic classification from raw DNA sequences that exploits the known hierarchical structure between labels for training. We provide a…
Learning Independent Causal Mechanisms
Giambattista Parascandolo, Niki Kilbertus, Mateo Rojas-Carulla +1
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 modeli…
Avoiding Discrimination through Causal Reasoning
Niki Kilbertus, Mateo Rojas-Carulla, Giambattista Parascandolo +3
Recent work on fairness in machine learning has focused on various statistical discrimination criteria and how they trade off. Most of these criteria are observational: They depend…
Discriminative k-shot learning using probabilistic models
Matthias Bauer, Mateo Rojas-Carulla, Jakub Bartłomiej Świątkowski +2
This paper introduces a probabilistic framework for k-shot image classification. The goal is to generalise from an initial large-scale classification task to a separate task compri…
Causal Discovery Using Proxy Variables
Mateo Rojas-Carulla, Marco Baroni, David Lopez-Paz
Discovering causal relations is fundamental to reasoning and intelligence. In particular, observational causal discovery algorithms estimate the cause-effect relation between two r…
Invariant Models for Causal Transfer Learning
Mateo Rojas-Carulla, Bernhard Schölkopf, Richard Turner +1
Methods of transfer learning try to combine knowledge from several related tasks (or domains) to improve performance on a test task. Inspired by causal methodology, we relax the us…