Jan Schuchardt

According to our database, Jan Schuchardt authored at least 18 papers between 2019 and 2026.

Collaborative distances:

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

2026

Provable Robustness against Backdoor Attacks via the Primal-Dual Perspective on Differential Privacy.

Aman Saxena, Jan Schuchardt, Yan Scholten, Stephan Günnemann

CoRR, May, 2026

Population Risk Bounds for Kolmogorov-Arnold Networks Trained by DP-SGD with Correlated Noise.

Puyu Wang, Jan Schuchardt, Nikita P. Kalinin, Junyu Zhou, Sophie Fellenz, Christoph Lampert, Marius Kloft

CoRR, May, 2026

Sampling-Free Privacy Accounting for Matrix Mechanisms under Random Allocation.

Jan Schuchardt, Nikita Kalinin

CoRR, January, 2026

Probabilistic Gray-Box Robustness Certification for Graph Neural Networks.

Jan Schuchardt

PhD thesis, 2026

Amplified Patch-Level Differential Privacy for Free via Random Cropping.

Kaan Durmaz, Jan Schuchardt, Sebastian Schmidt, Stephan Günnemann

Trans. Mach. Learn. Res., 2026

2025

Fast Proxies for LLM Robustness Evaluation.

Tim Beyer, Jan Schuchardt, Leo Schwinn, Stephan Günnemann

CoRR, February, 2025

Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting.

Jan Schuchardt, Mina Dalirrooyfard, Jed Guzelkabaagac, Anderson Schneider, Yuriy Nevmyvaka, Stephan Günnemann

Proceedings of the Forty-second International Conference on Machine Learning, 2025

2024

Group Privacy Amplification and Unified Amplification by Subsampling for Rényi Differential Privacy.

Jan Schuchardt, Mihail Stoian, Arthur Kosmala, Stephan Günnemann

CoRR, 2024

Unified Mechanism-Specific Amplification by Subsampling and Group Privacy Amplification.

Jan Schuchardt, Mihail Stoian, Arthur Kosmala, Stephan Günnemann

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

2023

Training Differentially Private Graph Neural Networks with Random Walk Sampling.

Morgane Ayle, Jan Schuchardt, Lukas Gosch, Daniel Zügner, Stephan Günnemann

CoRR, 2023

(Provable) Adversarial Robustness for Group Equivariant Tasks: Graphs, Point Clouds, Molecules, and More.

Jan Schuchardt, Yan Scholten, Stephan Günnemann

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Hierarchical Randomized Smoothing.

Yan Scholten, Jan Schuchardt, Aleksandar Bojchevski, Stephan Günnemann

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Localized Randomized Smoothing for Collective Robustness Certification.

Jan Schuchardt, Tom Wollschläger, Aleksandar Bojchevski, Stephan Günnemann

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

Invariance-Aware Randomized Smoothing Certificates.

Jan Schuchardt, Stephan Günnemann

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Randomized Message-Interception Smoothing: Gray-box Certificates for Graph Neural Networks.

Yan Scholten, Jan Schuchardt, Simon Geisler, Aleksandar Bojchevski, Stephan Günnemann

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Generalization of Neural Combinatorial Solvers Through the Lens of Adversarial Robustness.

Simon Geisler, Johanna Sommer, Jan Schuchardt, Aleksandar Bojchevski, Stephan Günnemann

Proceedings of the Tenth International Conference on Learning Representations, 2022

2021

Collective Robustness Certificates: Exploiting Interdependence in Graph Neural Networks.

Jan Schuchardt, Aleksandar Bojchevski, Johannes Klicpera, Stephan Günnemann

Proceedings of the 9th International Conference on Learning Representations, 2021

2019

Learning to Evolve.

Jan Schuchardt, Vladimir Golkov, Daniel Cremers

CoRR, 2019