IAM

DAVIDSTUTZ

TAG»DEEP LEARNING«

06thNOVEMBER2022

PROJECT

PhD thesis on uncertainty estimation and (adversarial) robustness in deep learning.

More ...

ARTICLE

PhD Defense Slides and Lessons Learned

In July this year I finally defended my PhD which mainly focused on (adversarial) robustness and uncertainty estimation in deep learning. In my case, the defense consisted of a (public) 30 minute talk about my work, followed by questions from the thesis committee and audience. In this article, I want to share the slides and some lessons learned in preparing for my defense.

More ...

18thAUGUST2022

PROJECT

Examples, tools and resources for using Caffe’s Python interface pyCaffe.

More ...

17thAUGUST2022

PROJECT

A template for extending PyTorch using C/CUDA operations.

More ...

17thAUGUST2022

PROJECT

Basic and advanced torch examples, template for implementing custom C/CUDA modules and implementations of variational auto-encoders.

More ...

16thAUGUST2022

PROJECT

3D mesh fusion, voxelization and evaluation for computer vision research.

More ...

ARTICLE

ICML 2022 Art of Robustness Paper “On Fragile Features and Batch Normalization in Adversarial Training”

While batch normalization has long been argued to increase adversarial vulnerability, it is still used in state-of-the-art adversarial training models. This is likely because of easier training and increased expressiveness. At the same time, recent papers argue that adversarial examples are partly caused by fragile features caused by learning spurious correlations. In this paper, we study the impact of batch normalization on utilizing these fragile features for robustness by fine-tuning only the batch normalization layers.

More ...

05thAUGUST2022

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 ...

04thAUGUST2022

PROJECT

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

More ...

ARTICLE

Machine Learning Security Seminar Talk “Relating Adversarially Robust Generalization to Flat Minima”

This week I was honored to speak at the Machine Learning Security Seminar organized by the Pattern Recognition and Applications Lab at University of Cagliari. I presented my work on relating adversarial robustness to flatness in the robust loss landscape, also touching on the relationship to weight robustness. In this article, I want to share the recording and slides of this talk.

More ...