activity
20242026
collaborators

9 papers

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

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

Puyu Wang, Jan Schuchardt, Nikita Kalinin +4

We establish the first population risk bounds for Kolmogorov-Arnold Networks (KANs) trained by mini-batch SGD with gradient clipping, covering non-private SGD as well as differenti…

cs.LG2026

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…

cs.LG2025

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…

cs.CR2025

Fast Proxies for LLM Robustness Evaluation

Tim Beyer, Jan Schuchardt, Leo Schwinn +1

Evaluating the robustness of LLMs to adversarial attacks is crucial for safe deployment, yet current red-teaming methods are often prohibitively expensive. We compare the ability o…