IAM

CATEGORY»RESEARCH;SELECTED COLLABORATIONS«

JANUARY2024

PROJECT

Adversarial training on a subset of (difficult) examples to improve efficiency.

More ...

JANUARY2024

PROJECT

Introducing slack control to improve accuracy and certified robustness with Lipschitz regularization.

More ...

JANUARY2024

PROJECT

Robustifying token attention for vision transformers.

More ...

JANUARY2024

PROJECT

Improve patch robustness of vision transformers.

More ...

SEPTEMBER2023

PROJECT

Achieving accuracy, fair and private image classification.

More ...

JUNE2023

PROJECT

Report of the 2020 Max Planck PhDNet survey results.

More ...

AUGUST2022

PROJECT

RESEARCH Fragile Features, Batch Normalization and Adversarial Training Outline Abstract Paper Poster News & Updates This is work led by Nils Walter. Quick links: Paper | Poster Abstract Modern deep learning architecture utilize batch normalization (BN) to stabilize training and improve accuracy. It has been shown that the BN layers alone are surprisingly expressive. In […]

More ...

AUGUST2022

PROJECT

Improving corruption and adversarial robustness by enhancing weak sub-networks.

More ...

MAY2020

PROJECT

Adversarial training on location-optimized adversarial patches.

More ...