9 papers
Measuring Security Without Fooling Ourselves: Why Benchmarking Agents Is Hard
Sahar Abdelnabi, Chris Hicks, Konrad Rieck +1
The benchmarks used to evaluate AI agents in security-critical roles suffer from crucial weaknesses. Building on recent empirical evidence, we characterize three core challenges th…
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…
Manipulating Feature Visualizations with Gradient Slingshots
Dilyara Bareeva, Marina M. -C. Höhne, Alexander Warnecke +5
Feature Visualization (FV) is a widely used technique for interpreting concepts learned by Deep Neural Networks (DNNs), which synthesizes input patterns that maximally activate a g…
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…