B-cos Alignment for Inherently Interpretable CNNs and Vision Transformers

1 code implementation • 19 Jun 2023 • Moritz Böhle, Navdeeppal Singh, Mario Fritz, Bernt Schiele

We present a new direction for increasing the interpretability of deep neural networks (DNNs) by promoting weight-input alignment during training.

White-Box Attacks on Hate-speech BERT Classifiers in German with Explicit and Implicit Character Level Defense

1 code implementation • 11 Feb 2022 • Shahrukh Khan, Mahnoor Shahid, Navdeeppal Singh

In this work, we evaluate the adversarial robustness of BERT models trained on German Hate Speech datasets.

Adversarial Robustness