Tobias Lorenz

According to our database, Tobias Lorenz authored at least 8 papers between 2018 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

Pixel-level Certified Explanations via Randomized Smoothing.

Alaa Anani, Tobias Lorenz, Mario Fritz, Bernt Schiele

CoRR, June, 2025

2024

BiCert: A Bilinear Mixed Integer Programming Formulation for Precise Certified Bounds Against Data Poisoning Attacks.

Tobias Lorenz, Marta Kwiatkowska, Mario Fritz

CoRR, 2024

Adaptive Hierarchical Certification for Segmentation using Randomized Smoothing.

Alaa Anani, Tobias Lorenz, Bernt Schiele, Mario Fritz

Proceedings of the Forty-first International Conference on Machine Learning, 2024

FullCert: Deterministic End-to-End Certification for Training and Inference of Neural Networks.

Tobias Lorenz, Marta Kwiatkowska, Mario Fritz

Proceedings of the Pattern Recognition, 2024

2023

Certifiers Make Neural Networks Vulnerable to Availability Attacks.

Tobias Lorenz, Marta Kwiatkowska, Mario Fritz

Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security, 2023

2021

Backdoor Attacks on Network Certification via Data Poisoning.

Tobias Lorenz, Marta Kwiatkowska, Mario Fritz

CoRR, 2021

Robustness Certification for Point Cloud Models.

Tobias Lorenz, Anian Ruoss, Mislav Balunovic, Gagandeep Singh, Martin T. Vechev

Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

2018

Feature Generating Networks for Zero-Shot Learning.

Yongqin Xian, Tobias Lorenz, Bernt Schiele, Zeynep Akata

Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018