4 citations · 16 across the 16 of their papers we have counts for
13 papers · 1 filter
Provable Robustness against Backdoor Attacks via the Primal-Dual Perspective on Differential Privacy
Aman Saxena, Jan Schuchardt, Yan Scholten +1
Randomized smoothing is a powerful tool for certifying robustness to adversarial perturbations, including poisoning attacks via randomized training and evasion attacks via randomiz…
Optimization Risk Bounds for Kolmogorov-Arnold Networks Trained by DP-SGD with Correlated Noise
Puyu Wang, Jan Schuchardt, Nikita Kalinin +5
The theoretical understanding of differentially private stochastic gradient descent (DP-SGD) with temporally correlated noise remains limited, particularly for non-convex neural ne…
Amplified Patch-Level Differential Privacy for Free via Random Cropping
Kaan Durmaz, Jan Schuchardt, Sebastian Schmidt +1
Random cropping is one of the most common data augmentation techniques in computer vision, yet the role of its inherent randomness in training differentially private machine learni…
Sampling-Free Privacy Accounting for Matrix Mechanisms under Random Allocation
Jan Schuchardt, Nikita Kalinin
We study privacy amplification for differentially private model training with matrix factorization under random allocation (also known as the balls-in-bins model). Recent work by C…
Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting
Jan Schuchardt, Mina Dalirrooyfard, Jed Guzelkabaagac +3
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 e…
Provable Adversarial Robustness for Group Equivariant Tasks: Graphs, Point Clouds, Molecules, and More
Jan Schuchardt, Yan Scholten, Stephan Günnemann
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 mo…
Hierarchical Randomized Smoothing
Yan Scholten, Jan Schuchardt, Aleksandar Bojchevski +1
Real-world data is complex and often consists of objects that can be decomposed into multiple entities (e.g. images into pixels, graphs into interconnected nodes). Randomized smoot…
Collective Robustness Certificates: Exploiting Interdependence in Graph Neural Networks
Jan Schuchardt, Aleksandar Bojchevski, Johannes Gasteiger +1
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…
Training Differentially Private Graph Neural Networks with Random Walk Sampling
Morgane Ayle, Jan Schuchardt, Lukas Gosch +2
Deep learning models are known to put the privacy of their training data at risk, which poses challenges for their safe and ethical release to the public. Differentially private st…
Randomized Message-Interception Smoothing: Gray-box Certificates for Graph Neural Networks
Yan Scholten, Jan Schuchardt, Simon Geisler +2
Randomized smoothing is one of the most promising frameworks for certifying the adversarial robustness of machine learning models, including Graph Neural Networks (GNNs). Yet, exis…
Invariance-Aware Randomized Smoothing Certificates
Jan Schuchardt, Stephan Günnemann
Building models that comply with the invariances inherent to different domains, such as invariance under translation or rotation, is a key aspect of applying machine learning to re…
Localized Randomized Smoothing for Collective Robustness Certification
Jan Schuchardt, Tom Wollschläger, Aleksandar Bojchevski +1
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…
Generalization of Neural Combinatorial Solvers Through the Lens of Adversarial Robustness
Simon Geisler, Johanna Sommer, Jan Schuchardt +2
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…