6 papers
Admissable: Training Reinforcement Learning Agents against Adversarial Missingness
Paul Stahlhofen, Luca Hermes, Tim Kochs +2
In order to make Reinforcement Learning algorithms applicable in real world scenarios, safety must be ensured even under adverse operating conditions. In this work, we consider the…
Noise Robust One-Class Intrusion Detection on Dynamic Graphs
Aleksei Liuliakov, Alexander Schulz, Luca Hermes +1
In the domain of network intrusion detection, robustness against contaminated and noisy data inputs remains a critical challenge. This study introduces a probabilistic version of t…
One-Class Intrusion Detection with Dynamic Graphs
Aleksei Liuliakov, Alexander Schulz, Luca Hermes +1
With the growing digitalization all over the globe, the relevance of network security becomes increasingly important. Machine learning-based intrusion detection constitutes a promi…
FashionFail: Addressing Failure Cases in Fashion Object Detection and Segmentation
Riza Velioglu, Robin Chan, Barbara Hammer
In the realm of fashion object detection and segmentation for online shopping images, existing state-of-the-art fashion parsing models encounter limitations, particularly when expo…
Targeted Visualization of the Backbone of Encoder LLMs
Isaac Roberts, Alexander Schulz, Luca Hermes +1
Attention based Large Language Models (LLMs) are the state-of-the-art in natural language processing (NLP). The two most common architectures are encoders such as BERT, and decoder…
Semantic Properties of cosine based bias scores for word embeddings
Sarah Schröder, Alexander Schulz, Fabian Hinder +1
Plenty of works have brought social biases in language models to attention and proposed methods to detect such biases. As a result, the literature contains a great deal of differen…