34 citations · 212 across the 70 of their papers we have counts for
20 papers · 1 filter
The Stable Artist: Steering Semantics in Diffusion Latent Space
Manuel Brack, Patrick Schramowski, Felix Friedrich +2
Large, text-conditioned generative diffusion models have recently gained a lot of attention for their impressive performance in generating high-fidelity images from text alone. How…
Boosting Object Representation Learning via Motion and Object Continuity
Quentin Delfosse, Wolfgang Stammer, Thomas Rothenbacher +2
Recent unsupervised multi-object detection models have shown impressive performance improvements, largely attributed to novel architectural inductive biases. Unfortunately, they ma…
Speaking Multiple Languages Affects the Moral Bias of Language Models
Katharina Hämmerl, Björn Deiseroth, Patrick Schramowski +4
Pre-trained multilingual language models (PMLMs) are commonly used when dealing with data from multiple languages and cross-lingual transfer. However, PMLMs are trained on varying…
Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models
Patrick Schramowski, Manuel Brack, Björn Deiseroth +1
Text-conditioned image generation models have recently achieved astonishing results in image quality and text alignment and are consequently employed in a fast-growing number of ap…
Rickrolling the Artist: Injecting Backdoors into Text Encoders for Text-to-Image Synthesis
Lukas Struppek, Dominik Hintersdorf, Kristian Kersting
While text-to-image synthesis currently enjoys great popularity among researchers and the general public, the security of these models has been neglected so far. Many text-guided i…
Revision Transformers: Instructing Language Models to Change their Values
Felix Friedrich, Wolfgang Stammer, Patrick Schramowski +1
Current transformer language models (LM) are large-scale models with billions of parameters. They have been shown to provide high performances on a variety of tasks but are also pr…
Exploiting Cultural Biases via Homoglyphs in Text-to-Image Synthesis
Lukas Struppek, Dominik Hintersdorf, Felix Friedrich +3
Models for text-to-image synthesis, such as DALL-E~2 and Stable Diffusion, have recently drawn a lot of interest from academia and the general public. These models are capable of p…
Does CLIP Know My Face?
Dominik Hintersdorf, Lukas Struppek, Manuel Brack +3
With the rise of deep learning in various applications, privacy concerns around the protection of training data have become a critical area of research. Whereas prior studies have…
Combining AI and AM - Improving Approximate Matching through Transformer Networks
Frieder Uhlig, Lukas Struppek, Dominik Hintersdorf +3
Approximate matching (AM) is a concept in digital forensics to determine the similarity between digital artifacts. An important use case of AM is the reliable and efficient detecti…
ILLUME: Rationalizing Vision-Language Models through Human Interactions
Manuel Brack, Patrick Schramowski, Björn Deiseroth +1
Bootstrapping from pre-trained language models has been proven to be an efficient approach for building vision-language models (VLM) for tasks such as image captioning or visual qu…
Attributions Beyond Neural Networks: The Linear Program Case
Florian Peter Busch, Matej Zečević, Kristian Kersting +1
Linear Programs (LPs) have been one of the building blocks in machine learning and have championed recent strides in differentiable optimizers for learning systems. While there exi…
Tearing Apart NOTEARS: Controlling the Graph Prediction via Variance Manipulation
Jonas Seng, Matej Zečević, Devendra Singh Dhami +1
Simulations are ubiquitous in machine learning. Especially in graph learning, simulations of Directed Acyclic Graphs (DAG) are being deployed for evaluating new algorithms. In the…
Machines Explaining Linear Programs
David Steinmann, Matej Zečević, Devendra Singh Dhami +1
There has been a recent push in making machine learning models more interpretable so that their performance can be trusted. Although successful, these methods have mostly focused o…
Adaptable Adapters
Nafise Sadat Moosavi, Quentin Delfosse, Kristian Kersting +1
State-of-the-art pretrained NLP models contain a hundred million to trillion parameters. Adapters provide a parameter-efficient alternative for the full finetuning in which we can…
Do Multilingual Language Models Capture Differing Moral Norms?
Katharina Hämmerl, Björn Deiseroth, Patrick Schramowski +3
Massively multilingual sentence representations are trained on large corpora of uncurated data, with a very imbalanced proportion of languages included in the training. This may ca…
Neuro-Symbolic Verification of Deep Neural Networks
Xuan Xie, Kristian Kersting, Daniel Neider
Formal verification has emerged as a powerful approach to ensure the safety and reliability of deep neural networks. However, current verification tools are limited to only a handf…
A Typology for Exploring the Mitigation of Shortcut Behavior
Felix Friedrich, Wolfgang Stammer, Patrick Schramowski +1
As machine learning models become increasingly larger, trained weakly supervised on large, possibly uncurated data sets, it becomes increasingly important to establish mechanisms f…
Can Machines Help Us Answering Question 16 in Datasheets, and In Turn Reflecting on Inappropriate Content?
Patrick Schramowski, Christopher Tauchmann, Kristian Kersting
Large datasets underlying much of current machine learning raise serious issues concerning inappropriate content such as offensive, insulting, threatening, or might otherwise cause…
Right for the Right Latent Factors: Debiasing Generative Models via Disentanglement
Xiaoting Shao, Karl Stelzner, Kristian Kersting
A key assumption of most statistical machine learning methods is that they have access to independent samples from the distribution of data they encounter at test time. As such, th…
Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks
Lukas Struppek, Dominik Hintersdorf, Antonio De Almeida Correia +2
Model inversion attacks (MIAs) aim to create synthetic images that reflect the class-wise characteristics from a target classifier's private training data by exploiting the model's…