7 papers
Validating, Not Sampling: Region-Level Robustness of Vision-Language and Vision-Language-Action Models
Bogdan Aron, Christopher Brix, Benedikt Brückner +3
Vision-language models (VLMs) and vision-language-action models (VLAs) are increasingly deployed in real-world applications. There, a small perturbation to the recorded camera imag…
Certified Training for Convolutional Perturbations
Benedikt Brückner, Alessio Lomuscio
Vision models have been found to be susceptible to perturbations such as motion blur induced at runtime by a shaking camera. This impedes their deployment in critical applications…
Hybrid Robustness Verification for Spatio-Temporal Neural Networks
Sherwin Varghese, Matthew Wicker, Alessio Lomuscio
With AI increasingly deployed in safety-critical systems, providing formal robustness guarantees for the underlying models is essential. Existing verification methods either rely o…
Lipschitz Optimization for Formal Verification of Homographies
Jean-Guillaume Durand, Panagiotis Kouvaros, Maxime Gariel +1
The adoption of vision neural networks in regulated industries requires formal robustness guarantees, especially in safety-critical domains such as healthcare, autonomous vehicles,…
A Robust Out-of-Distribution Detection Framework via Synergistic Smoothing
Maria Stoica, Abdelrahman Hekal, Alessio Lomuscio
Reliable out-of-distribution (OOD) detection is a critical requirement for the safe deployment of machine learning systems. Despite recent progress, state-of-the-art OOD detectors…
IoUCert: Robustness Verification for Anchor-based Object Detectors
Benedikt Brückner, Alejandro J. Mercado, Yanghao Zhang +2
While formal robustness verification has seen significant success in image classification, scaling these guarantees to object detection remains notoriously difficult due to complex…
Out-of-Distribution Detection using Counterfactual Distance
Maria Stoica, Francesco Leofante, Alessio Lomuscio
Accurate and explainable out-of-distribution (OOD) detection is required to use machine learning systems safely. Previous work has shown that feature distance to decision boundarie…