AIConfPaper
← Search

Jan Schuchardt

9 accepted papers

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
ICML 2025spotlight

Many forms of sensitive data, such as web traffic, mobility data, or hospital occupancy, are inherently sequential. The standard method for training machine learning models while ensuring privacy for units of sensitive information, such as individual hospital visits, is differentially private stocha…

Cited by 0Source ↗PDF ↗Scholar ↗
2024

Unified Mechanism-Specific Amplification by Subsampling and Group Privacy Amplification

Jan Schuchardt, Mihail Stoian, Arthur Kosmala, Stephan Günnemann
NeurIPS 2024poster

Amplification by subsampling is one of the main primitives in machine learning with differential privacy (DP): Training a model on random batches instead of complete datasets results in stronger privacy. This is traditionally formalized via mechanism-agnostic subsampling guarantees that express the…

Cited by 2Source ↗PDF ↗Scholar ↗
2023

Localized Randomized Smoothing for Collective Robustness Certification

Jan Schuchardt, Tom Wollschläger, Aleksandar Bojchevski, Stephan Günnemann
ICLR 2023top-25%

Models for image segmentation, node classification and many other tasks map a single input to multiple labels. By perturbing this single shared input (e.g. the image) an adversary can manipulate several predictions (e.g. misclassify several pixels). Collective robustness certification is the task of…

Cited by 11Source ↗PDF ↗Scholar ↗
2023

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

Jan Schuchardt, Yan Scholten, Stephan Günnemann
NeurIPS 2023poster

A machine learning model is traditionally considered robust if its prediction remains (almost) constant under input perturbations with small norm. However, real-world tasks like molecular property prediction or point cloud segmentation have inherent equivariances, such as rotation or permutation equ…

Cited by 4Source ↗PDF ↗Scholar ↗
2022

Generalization of Neural Combinatorial Solvers Through the Lens of Adversarial Robustness

Simon Geisler, Johanna Sommer, Jan Schuchardt, Aleksandar Bojchevski, Stephan Günnemann
ICLR 2022poster

End-to-end (geometric) deep learning has seen first successes in approximating the solution of combinatorial optimization problems. However, generating data in the realm of NP-hard/-complete tasks brings practical and theoretical challenges, resulting in evaluation protocols that are too optimistic.…

Cited by 51Source ↗PDF ↗Scholar ↗
2022

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

Yan Scholten, Jan Schuchardt, Simon Geisler, Aleksandar Bojchevski, Stephan Günnemann
NeurIPS 2022accept

Randomized smoothing is one of the most promising frameworks for certifying the adversarial robustness of machine learning models, including Graph Neural Networks (GNNs). Yet, existing randomized smoothing certificates for GNNs are overly pessimistic since they treat the model as a black box, ignori…

Cited by 25Source ↗PDF ↗Scholar ↗
2021

Collective Robustness Certificates: Exploiting Interdependence in Graph Neural Networks

Jan Schuchardt, Aleksandar Bojchevski, Johannes Gasteiger, Stephan Günnemann
ICLR 2021poster

In tasks like node classification, image segmentation, and named-entity recognition we have a classifier that simultaneously outputs multiple predictions (a vector of labels) based on a single input, i.e. a single graph, image, or document respectively. Existing adversarial robustness certificates c…

Cited by 33Source ↗PDF ↗Scholar ↗