17 citations · 20 across the 9 of their papers we have counts for
6 papers · 1 filter
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…
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…
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…
Adaptive Hierarchical Certification for Segmentation using Randomized Smoothing
Alaa Anani, Tobias Lorenz, Bernt Schiele +1
Certification for machine learning is proving that no adversarial sample can evade a model within a range under certain conditions, a necessity for safety-critical domains. Common…
Certifiers Make Neural Networks Vulnerable to Availability Attacks
Tobias Lorenz, Marta Kwiatkowska, Mario Fritz
To achieve reliable, robust, and safe AI systems, it is vital to implement fallback strategies when AI predictions cannot be trusted. Certifiers for neural networks are a reliable…
Robustness Certification for Point Cloud Models
Tobias Lorenz, Anian Ruoss, Mislav Balunović +2
The use of deep 3D point cloud models in safety-critical applications, such as autonomous driving, dictates the need to certify the robustness of these models to real-world transfo…