353 citations · 1.3k across the 38 of their papers we have counts for
44 papers
Get a GRIP, this will be a long TRIP: A Quantifiable Long-Range Framework for Verifying Over-squashing
Ferran Hernandez Caralt, Simon Heilig, Adrián Bazaga +3
Empirical claims about the connection between over-squashing and long-range interactions in GNNs, can only be trusted if the benchmarks used to validate them genuinely require long…
A Critical Audit of Spatiotemporal Forecasting Benchmark Datasets and Models
Kenneth Martin, Simon Heilig, Asja Fischer +3
Graph neural networks (GNNs) are routinely employed for spatiotemporal forecasting, yet their performance across widely used benchmark datasets is inconsistent. Here, we perform an…
DepthKV: Layer-Dependent KV Cache Pruning for Long-Context LLM Inference
Zahra Dehghanighobadi, Asja Fischer
Long-context reasoning is a critical capability of large language models (LLMs), enabling applications such as long-document understanding, summarization, and code generation. Howe…
Set-Membership Inference Attacks using Data Watermarking
Mike Laszkiewicz, Denis Lukovnikov, Johannes Lederer +1
In this work, we propose a set-membership inference attack for generative models using deep image watermarking techniques. In particular, we demonstrate how conditional sampling fr…
Single-Model Attribution of Generative Models Through Final-Layer Inversion
Mike Laszkiewicz, Jonas Ricker, Johannes Lederer +1
Recent breakthroughs in generative modeling have sparked interest in practical single-model attribution. Such methods predict whether a sample was generated by a specific generator…
DistriBlock: Identifying adversarial audio samples by leveraging characteristics of the output distribution
Matías Pizarro, Dorothea Kolossa, Asja Fischer
Adversarial attacks can mislead automatic speech recognition (ASR) systems into predicting an arbitrary target text, thus posing a clear security threat. To prevent such attacks, w…
Uncertainty-based Detection of Adversarial Attacks in Semantic Segmentation
Kira Maag, Asja Fischer
State-of-the-art deep neural networks have proven to be highly powerful in a broad range of tasks, including semantic image segmentation. However, these networks are vulnerable aga…
Information Plane Analysis for Dropout Neural Networks
Linara Adilova, Bernhard C. Geiger, Asja Fischer
The information-theoretic framework promises to explain the predictive power of neural networks. In particular, the information plane analysis, which measures mutual information (M…
Towards the Detection of Diffusion Model Deepfakes
Jonas Ricker, Simon Damm, Thorsten Holz +1
In the course of the past few years, diffusion models (DMs) have reached an unprecedented level of visual quality. However, relatively little attention has been paid to the detecti…
Marginal Tail-Adaptive Normalizing Flows
Mike Laszkiewicz, Johannes Lederer, Asja Fischer
Learning the tail behavior of a distribution is a notoriously difficult problem. By definition, the number of samples from the tail is small, and deep generative models, such as no…
How Sampling Impacts the Robustness of Stochastic Neural Networks
Sina Däubener, Asja Fischer
Stochastic neural networks (SNNs) are random functions whose predictions are gained by averaging over multiple realizations. Consequently, a gradient-based adversarial example is c…
Robustifying automatic speech recognition by extracting slowly varying features
Matías Pizarro, Dorothea Kolossa, Asja Fischer
In the past few years, it has been shown that deep learning systems are highly vulnerable under attacks with adversarial examples. Neural-network-based automatic speech recognition…
Copula-Based Normalizing Flows
Mike Laszkiewicz, Johannes Lederer, Asja Fischer
Normalizing flows, which learn a distribution by transforming the data to samples from a Gaussian base distribution, have proven powerful density approximations. But their expressi…
A Novel Regression Loss for Non-Parametric Uncertainty Optimization
Joachim Sicking, Maram Akila, Maximilian Pintz +3
Quantification of uncertainty is one of the most promising approaches to establish safe machine learning. Despite its importance, it is far from being generally solved, especially…
Wasserstein Dropout
Joachim Sicking, Maram Akila, Maximilian Pintz +3
Despite of its importance for safe machine learning, uncertainty quantification for neural networks is far from being solved. State-of-the-art approaches to estimate neural uncerta…
The ELBO of Variational Autoencoders Converges to a Sum of Three Entropies
Simon Damm, Dennis Forster, Dmytro Velychko +3
The central objective function of a variational autoencoder (VAE) is its variational lower bound (the ELBO). Here we show that for standard (i.e., Gaussian) VAEs the ELBO converges…
Investigating maximum likelihood based training of infinite mixtures for uncertainty quantification
Sina Däubener, Asja Fischer
Uncertainty quantification in neural networks gained a lot of attention in the past years. The most popular approaches, Bayesian neural networks (BNNs), Monte Carlo dropout, and de…
Improving the Long-Range Performance of Gated Graph Neural Networks
Denis Lukovnikov, Jens Lehmann, Asja Fischer
Many popular variants of graph neural networks (GNNs) that are capable of handling multi-relational graphs may suffer from vanishing gradients. In this work, we propose a novel GNN…
Characteristics of Monte Carlo Dropout in Wide Neural Networks
Joachim Sicking, Maram Akila, Tim Wirtz +2
Monte Carlo (MC) dropout is one of the state-of-the-art approaches for uncertainty estimation in neural networks (NNs). It has been interpreted as approximately performing Bayesian…
On the convergence of the Metropolis algorithm with fixed-order updates for multivariate binary probability distributions
Kai Brügge, Asja Fischer, Christian Igel
The Metropolis algorithm is arguably the most fundamental Markov chain Monte Carlo (MCMC) method. But the algorithm is not guaranteed to converge to the desired distribution in the…
Bringing Light Into the Dark: A Large-scale Evaluation of Knowledge Graph Embedding Models Under a Unified Framework
Mehdi Ali, Max Berrendorf, Charles Tapley Hoyt +6
The heterogeneity in recently published knowledge graph embedding models' implementations, training, and evaluation has made fair and thorough comparisons difficult. In order to as…
Unsupervised Cross-Domain Speech-to-Speech Conversion with Time-Frequency Consistency
Mohammad Asif Khan, Fabien Cardinaux, Stefan Uhlich +2
In recent years generative adversarial network (GAN) based models have been successfully applied for unsupervised speech-to-speech conversion.The rich compact harmonic view of the…
Detecting Adversarial Examples for Speech Recognition via Uncertainty Quantification
Sina Däubener, Lea Schönherr, Asja Fischer +1
Machine learning systems and also, specifically, automatic speech recognition (ASR) systems are vulnerable against adversarial attacks, where an attacker maliciously changes the in…
Thresholded Adaptive Validation: Tuning the Graphical Lasso for Graph Recovery
Mike Laszkiewicz, Asja Fischer, Johannes Lederer
Many Machine Learning algorithms are formulated as regularized optimization problems, but their performance hinges on a regularization parameter that needs to be calibrated to each…