1k citations · 4.2k across the 120 of their papers we have counts for
23 papers · 1 filter
Exact Certification of (Graph) Neural Networks Against Label Poisoning
Mahalakshmi Sabanayagam, Lukas Gosch, Stephan Günnemann +1
Machine learning models are highly vulnerable to label flipping, i.e., the adversarial modification (poisoning) of training labels to compromise performance. Thus, deriving robustn…
Extracting Unlearned Information from LLMs with Activation Steering
Atakan Seyitoğlu, Aleksei Kuvshinov, Leo Schwinn +1
An unintended consequence of the vast pretraining of Large Language Models (LLMs) is the verbatim memorization of fragments of their training data, which may contain sensitive or c…
Unlocking Point Processes through Point Set Diffusion
David Lüdke, Enric Rabasseda Raventós, Marcel Kollovieh +1
Point processes model the distribution of random point sets in mathematical spaces, such as spatial and temporal domains, with applications in fields like seismology, neuroscience,…
Provably Reliable Conformal Prediction Sets in the Presence of Data Poisoning
Yan Scholten, Stephan Günnemann
Conformal prediction provides model-agnostic and distribution-free uncertainty quantification through prediction sets that are guaranteed to include the ground truth with any user-…
A Probabilistic Perspective on Unlearning and Alignment for Large Language Models
Yan Scholten, Stephan Günnemann, Leo Schwinn
Comprehensive evaluation of Large Language Models (LLMs) is an open research problem. Existing evaluations rely on deterministic point estimates generated via greedy decoding. Howe…
Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecasting
Marcel Kollovieh, Marten Lienen, David Lüdke +2
Recent advancements in generative modeling, particularly diffusion models, have opened new directions for time series modeling, achieving state-of-the-art performance in forecastin…
Certifiably Robust Encoding Schemes
Aman Saxena, Tom Wollschläger, Nicola Franco +2
Quantum machine learning uses principles from quantum mechanics to process data, offering potential advances in speed and performance. However, previous work has shown that these m…
Discrete Randomized Smoothing Meets Quantum Computing
Tom Wollschläger, Aman Saxena, Nicola Franco +2
Breakthroughs in machine learning (ML) and advances in quantum computing (QC) drive the interdisciplinary field of quantum machine learning to new levels. However, due to the susce…
Expressivity and Generalization: Fragment-Biases for Molecular GNNs
Tom Wollschläger, Niklas Kemper, Leon Hetzel +2
Although recent advances in higher-order Graph Neural Networks (GNNs) improve the theoretical expressiveness and molecular property predictive performance, they often fall short of…
Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attacks
Lukas Gosch, Mahalakshmi Sabanayagam, Debarghya Ghoshdastidar +1
Generalization of machine learning models can be severely compromised by data poisoning, where adversarial changes are applied to the training data. This vulnerability has led to i…
Predicting Probabilities of Error to Combine Quantization and Early Exiting: QuEE
Florence Regol, Joud Chataoui, Bertrand Charpentier +3
Machine learning models can solve complex tasks but often require significant computational resources during inference. This has led to the development of various post-training com…
Energy-based Epistemic Uncertainty for Graph Neural Networks
Dominik Fuchsgruber, Tom Wollschläger, Stephan Günnemann
In domains with interdependent data, such as graphs, quantifying the epistemic uncertainty of a Graph Neural Network (GNN) is challenging as uncertainty can arise at different stru…
Efficient Time Series Processing for Transformers and State-Space Models through Token Merging
Leon Götz, Marcel Kollovieh, Stephan Günnemann +1
Despite recent advances in subquadratic attention mechanisms or state-space models, processing long token sequences still imposes significant computational requirements. Token merg…
Efficient Adversarial Training in LLMs with Continuous Attacks
Sophie Xhonneux, Alessandro Sordoni, Stephan Günnemann +2
Large language models (LLMs) are vulnerable to adversarial attacks that can bypass their safety guardrails. In many domains, adversarial training has proven to be one of the most p…
A Unified Approach Towards Active Learning and Out-of-Distribution Detection
Sebastian Schmidt, Leonard Schenk, Leo Schwinn +1
When applying deep learning models in open-world scenarios, active learning (AL) strategies are crucial for identifying label candidates from a nearly infinite amount of unlabeled…
Uncertainty for Active Learning on Graphs
Dominik Fuchsgruber, Tom Wollschläger, Bertrand Charpentier +2
Uncertainty Sampling is an Active Learning strategy that aims to improve the data efficiency of machine learning models by iteratively acquiring labels of data points with the high…
Finding Dino: A Plug-and-Play Framework for Zero-Shot Detection of Out-of-Distribution Objects Using Prototypes
Poulami Sinhamahapatra, Franziska Schwaiger, Shirsha Bose +3
Detecting and localising unknown or out-of-distribution (OOD) objects in any scene can be a challenging task in vision, particularly in safety-critical cases involving autonomous s…
Enhancing Interpretability of Vertebrae Fracture Grading using Human-interpretable Prototypes
Poulami Sinhamahapatra, Suprosanna Shit, Anjany Sekuboyina +7
Vertebral fracture grading classifies the severity of vertebral fractures, which is a challenging task in medical imaging and has recently attracted Deep Learning (DL) models. Only…
Structurally Prune Anything: Any Architecture, Any Framework, Any Time
Xun Wang, John Rachwan, Stephan Günnemann +1
Neural network pruning serves as a critical technique for enhancing the efficiency of deep learning models. Unlike unstructured pruning, which only sets specific parameters to zero…
Unified Mechanism-Specific Amplification by Subsampling and Group Privacy Amplification
Jan Schuchardt, Mihail Stoian, Arthur Kosmala +1
Amplification by subsampling is one of the main primitives in machine learning with differential privacy (DP): Training a model on random batches instead of complete datasets resul…
Shaving Weights with Occam's Razor: Bayesian Sparsification for Neural Networks Using the Marginal Likelihood
Rayen Dhahri, Alexander Immer, Betrand Charpentier +2
Neural network sparsification is a promising avenue to save computational time and memory costs, especially in an age where many successful AI models are becoming too large to naïv…
Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space
Leo Schwinn, David Dobre, Sophie Xhonneux +2
Current research in adversarial robustness of LLMs focuses on discrete input manipulations in the natural language space, which can be directly transferred to closed-source models.…
Provable Adversarial Robustness for Group Equivariant Tasks: Graphs, Point Clouds, Molecules, and More
Jan Schuchardt, Yan Scholten, Stephan Günnemann
A machine learning model is traditionally considered robust if its prediction remains (almost) constant under input perturbations with small norm. However, real-world tasks like mo…