7 papers
False Prophets: On the Security of World Models in Agentic Systems
Erik Imgrund, Anna Wimbauer, Klim Kireev +1
Large language models now power autonomous agents capable of complex, multi-step tasks in different environments. Accurate and reliable execution of these tasks requires the agent…
Fingerprinting Inference Systems of Large Language Models
Anna Wimbauer, Jonas Möller, Erik Imgrund +1
The behavior of LLMs does not depend solely on the model itself. Components of the inference system, such as the inference engine, attention backend, and hardware platform, subtly…
When a Zero-Shooter Cheats: Improving Age Estimation via Activation Steering
Erik Imgrund, Pia Hanfeld, Klim Kireev +1
Different age-related regulations have been proposed to protect minors from harmful content and interactions online. Automated age estimation is central to enforcing such regulatio…
Hardware-Triggered Backdoors
Jonas Möller, Erik Imgrund, Thorsten Eisenhofer +1
Machine learning models are routinely deployed on a wide range of computing hardware. Although such hardware is typically expected to produce identical results, differences in its…
LLM-based Vulnerability Discovery through the Lens of Code Metrics
Felix Weissberg, Lukas Pirch, Erik Imgrund +3
Large language models (LLMs) excel in many tasks of software engineering, yet progress in leveraging them for vulnerability discovery has stalled in recent years. To understand thi…
Adversarial Observations in Weather Forecasting
Erik Imgrund, Thorsten Eisenhofer, Konrad Rieck
AI-based systems, such as Google's GenCast, have recently redefined the state of the art in weather forecasting, offering more accurate and timely predictions of both everyday weat…