publications

publications by categories in reversed chronological order. generated by jekyll-scholar.

2026

  1. Provable Robustness against Backdoor Attacks via the Primal-Dual Perspective on Differential Privacy
    Aman Saxena, Jan Schuchardt, Yan Scholten, and Stephan Günnemann
    arXiv preprint arXiv:2605.21780, 2026
    arXiv
  2. Population Risk Bounds for Kolmogorov-Arnold Networks Trained by DP-SGD with Correlated Noise
    Puyu Wang, Jan Schuchardt, Nikita Kalinin, Junyu Zhou, Sophie Fellenz, and 2 more authors
    arXiv preprint arXiv:2605.12648, 2026
    arXiv
  3. Sampling-Free Privacy Accounting for Matrix Mechanisms under Random Allocation
    Jan Schuchardt and Nikita Kalinin
    arXiv preprint arXiv:2601.21636, 2026
    arXiv
  4. Probabilistic Gray-Box Robustness Certification for Graph Neural Networks
    Jan Schuchardt
    Technische Universität München, 2026
    HTML
  5. Amplified Patch-Level Differential Privacy for Free via Random Cropping
    Kaan Durmaz, Jan Schuchardt, Sebastian Schmidt, and Stephan Günnemann
    Transactions on Machine Learning Research, 2026
    arXiv

2025

  1. Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting
    Jan Schuchardt, Mina Dalirrooyfard, Jed Guzelkabaagac, Anderson Schneider, Yuriy Nevmyvaka, and 1 more author
    In International Conference on Machine Learning, 2025
    arXiv
  2. Fast Proxies for LLM Robustness Evaluation
    Tim Beyer, Jan Schuchardt, Leo Schwinn, and Stephan Günnemann
    In ICLR 2025 Workshop on Building Trust in Language Models and Applications, 2025
    arXiv

2024

  1. Unified Mechanism-Specific Amplification by Subsampling and Group Privacy Amplification
    Jan Schuchardt, Mihail Stoian, Arthur Kosmala, and Stephan Günnemann
    In Advances in Neural Information Processing Systems, 2024
    arXiv

2023

  1. Provable Adversarial Robustness for Group Equivariant Tasks: Graphs, Point Clouds, Molecules, and More
    Jan Schuchardt, Yan Scholten, and Stephan Günnemann
    In Advances in Neural Information Processing Systems, 2023
    arXiv
  2. Hierarchical Randomized Smoothing
    Yan Scholten, Jan Schuchardt, Aleksandar Bojchevski, and Stephan Günnemann
    In Advances in Neural Information Processing Systems, 2023
    arXiv
  3. Localized Randomized Smoothing for Collective Robustness Certification
    Jan Schuchardt, Tom Wollschläger, Aleksandar Bojchevski, and Stephan Günnemann
    In International Conference on Learning Representations, 2023
    arXiv

2022

  1. Training Differentially Private Graph Neural Networks with Random Walk Sampling
    Morgane Ayle, Jan Schuchardt, Lukas Gosch, Daniel Zügner, and Stephan Günnemann
    In Workshop on Trustworthy and Socially Responsible Machine Learning, NeurIPS, 2022
    arXiv
  2. Invariance-Aware Randomized Smoothing Certificates
    Jan Schuchardt and Stephan Günnemann
    In Advances in Neural Information Processing Systems, 2022
    arXiv
  3. Randomized Message-Interception Smoothing: Gray-box Certificates for Graph Neural Networks
    Yan Scholten, Jan Schuchardt, Simon Geisler, Aleksandar Bojchevski, and Stephan Günnemann
    In Advances in Neural Information Processing Systems, 2022
    arXiv
  4. Generalization of Neural Combinatorial Solvers Through the Lens of Adversarial Robustness
    Simon Geisler, Johanna Sommer, Jan Schuchardt, Aleksandar Bojchevski, and Stephan Günnemann
    In International Conference on Learning Representations, 2022
    arXiv

2021

  1. Collective Robustness Certificates: Exploiting Interdependence in Graph Neural Networks
    Jan Schuchardt, Aleksandar Bojchevski, Johannes Gasteiger, and Stephan Günnemann
    In International Conference on Learning Representations, 2021
    arXiv