4 citations · 16 across the 16 of their papers we have counts for
4 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…