7 papers
The Oracle's Gambit: A Game-Theoretic Framework for Responsible AI Release
Christoph R. Landolt, Tobias Lorenz, Marta Kwiatkowska +1
Responsible vulnerability disclosure can secure the defender's head start by controlling when a vulnerability becomes public. However, this status quo is now challenged by increase…
Certified Circuits: Stability Guarantees for Mechanistic Circuits
Alaa Anani, Tobias Lorenz, Bernt Schiele +2
Understanding how neural networks arrive at their predictions is essential for debugging, auditing, and deployment. Mechanistic interpretability pursues this goal by identifying ci…
Scalable Delphi: Large Language Models for Structured Risk Estimation
Tobias Lorenz, Mario Fritz
Quantitative risk assessment in high-stakes domains relies on structured expert elicitation to estimate unobservable properties. The gold standard - the Delphi method - produces ca…
MIBP-Cert: Certified Training against Data Perturbations with Mixed-Integer Bilinear Programs
Tobias Lorenz, Marta Kwiatkowska, Mario Fritz
Data errors, corruptions, and poisoning attacks during training pose a major threat to the reliability of modern AI systems. While extensive effort has gone into empirical mitigati…
Pixel-level Certified Explanations via Randomized Smoothing
Alaa Anani, Tobias Lorenz, Mario Fritz +1
Post-hoc attribution methods aim to explain deep learning predictions by highlighting influential input pixels. However, these explanations are highly non-robust: small, impercepti…
FullCert: Deterministic End-to-End Certification for Training and Inference of Neural Networks
Tobias Lorenz, Marta Kwiatkowska, Mario Fritz
Modern machine learning models are sensitive to the manipulation of both the training data (poisoning attacks) and inference data (adversarial examples). Recognizing this issue, th…