| 2025 | ICCV | DASH: Detection and Assessment of Systematic Hallucinations of VLMs. | Maximilian Augustin, Yannic Neuhaus, Matthias Hein |
| 2025 | ICML | An Interpretable N-gram Perplexity Threat Model for Large Language Model Jailbreaks. | Valentyn Boreiko, Alexander Panfilov, Vclav Vorcek, Matthias Hein, Jonas Geiping |
| 2025 | ICML | Mahalanobis++: Improving OOD Detection via Feature Normalization. | Maximilian Mller, Matthias Hein |
| 2025 | MICCAI | Segmenting Brain Regions in Low Field Pediatric Brain MR Images Using (Symmetric) NnU-Net ResEnc. | Jan Nikolas Morshuis, Matthias Hein, Christian F. Baumgartner |
| 2025 | MICCAI | Utilizing an Ensemble of 3D U-Nets to Predict High-Field MRI T1-, T2-, and FLAIR-Images from Ultra-Low-Field MRI Images. | Jan Nikolas Morshuis, Matthias Hein, Christian F. Baumgartner |
| 2025 | MICCAI | Mind the Detail: Uncovering Clinically Relevant Image Details in Accelerated MRI with Semantically Diverse Reconstructions. | Jan Nikolas Morshuis, Christian Schlarmann, Thomas Kstner, Christian F. Baumgartner, Matthias Hein |
| 2024 | CVPR | DiG-IN: Diffusion Guidance for Investigating Networks - Uncovering Classifier Differences, Neuron Visualisations, and Visual Counterfactual Explanations. | Maximilian Augustin, Yannic Neuhaus, Matthias Hein |
| 2024 | ECCV | Towards Reliable Evaluation and Fast Training of Robust Semantic Segmentation Models. | Francesco Croce, Naman D. Singh, Matthias Hein |
| 2024 | ICML | Bias of Stochastic Gradient Descent or the Architecture: Disentangling the Effects of Overparameterization of Neural Networks. | Amit Peleg, Matthias Hein |
| 2024 | ICML | Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models. | Christian Schlarmann, Naman Deep Singh, Francesco Croce, Matthias Hein |
| 2024 | MICCAI | Segmentation-Guided MRI Reconstruction for Meaningfully Diverse Reconstructions. | Jan Nikolas Morshuis, Matthias Hein, Christian F. Baumgartner |
| 2023 | ICCV | Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNet. | Yannic Neuhaus, Maximilian Augustin, Valentyn Boreiko, Matthias Hein |
| 2023 | ICLR | Sound Randomized Smoothing in Floating-Point Arithmetic. | Vclav Vorcek, Matthias Hein |
| 2023 | ICLR | Certified Defences Against Adversarial Patch Attacks on Semantic Segmentation. | Maksym Yatsura, Kaspar Sakmann, N. Grace Hua, Matthias Hein, Jan Hendrik Metzen |
| 2023 | ICML | A Modern Look at the Relationship between Sharpness and Generalization. | Maksym Andriushchenko, Francesco Croce, Maximilian Mller, Matthias Hein, Nicolas Flammarion |
| 2023 | ICML | In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation. | Julian Bitterwolf, Maximilian Mller, Matthias Hein |
| 2023 | ICML | Improving l1-Certified Robustness via Randomized Smoothing by Leveraging Box Constraints. | Vclav Vorcek, Matthias Hein |
| 2022 | AAAI | Sparse-RS: A Versatile Framework for Query-Efficient Sparse Black-Box Adversarial Attacks. | Francesco Croce, Maksym Andriushchenko, Naman D. Singh, Nicolas Flammarion, Matthias Hein |
| 2022 | AISTATS | Being a Bit Frequentist Improves Bayesian Neural Networks. | Agustinus Kristiadi, Matthias Hein, Philipp Hennig |
| 2022 | ICML | Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantities. | Julian Bitterwolf, Alexander Meinke, Maximilian Augustin, Matthias Hein |
| 2022 | ICML | Adversarial Robustness against Multiple and Single l | Francesco Croce, Matthias Hein |
| 2022 | ICML | Evaluating the Adversarial Robustness of Adaptive Test-time Defenses. | Francesco Croce, Sven Gowal, Thomas Brunner, Evan Shelhamer, Matthias Hein, A. Taylan Cemgil |
| 2022 | ICML | Provably Adversarially Robust Nearest Prototype Classifiers. | Vclav Vorcek, Matthias Hein |
| 2022 | MICCAI | Visual Explanations for the Detection of Diabetic Retinopathy from Retinal Fundus Images. | Valentyn Boreiko, Indu Ilanchezian, Murat Sekin Ayhan, Sarah Mller, Lisa M. Koch, Hanna Faber, Philipp Berens, Matthias Hein |
| 2022 | MICCAI | Adversarial Robustness of MR Image Reconstruction Under Realistic Perturbations. | Jan Nikolas Morshuis, Sergios Gatidis, Matthias Hein, Christian F. Baumgartner |
| 2022 | SoCS | Neural Network Heuristic Functions: Taking Confidence into Account. | Daniel Heller, Patrick Ferber, Julian Bitterwolf, Matthias Hein, Jrg Hoffmann |
| 2021 | ICCV | Relating Adversarially Robust Generalization to Flat Minima. | David Stutz, Matthias Hein, Bernt Schiele |
| 2021 | ICML | Mind the Box: l | Francesco Croce, Matthias Hein |
| 2021 | UAI | Learnable uncertainty under Laplace approximations. | Agustinus Kristiadi, Matthias Hein, Philipp Hennig |
| 2020 | ECCV | Square Attack: A Query-Efficient Black-Box Adversarial Attack via Random Search. | Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion, Matthias Hein |
| 2020 | ECCV | Adversarial Robustness on In- and Out-Distribution Improves Explainability. | Maximilian Augustin, Alexander Meinke, Matthias Hein |
| 2020 | ICLR | Provable robustness against all adversarial $l_p$-perturbations for $p\geq 1$. | Francesco Croce, Matthias Hein |
| 2020 | ICLR | Towards neural networks that provably know when they don't know. | Alexander Meinke, Matthias Hein |
| 2020 | ICML | Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attack. | Francesco Croce, Matthias Hein |
| 2020 | ICML | Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks. | Francesco Croce, Matthias Hein |
| 2020 | ICML | Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks. | Agustinus Kristiadi, Matthias Hein, Philipp Hennig |
| 2020 | ICML | Confidence-Calibrated Adversarial Training: Generalizing to Unseen Attacks. | David Stutz, Matthias Hein, Bernt Schiele |
| 2019 | AISTATS | Provable Robustness of ReLU networks via Maximization of Linear Regions. | Francesco Croce, Maksym Andriushchenko, Matthias Hein |
| 2019 | CVPR | Why ReLU Networks Yield High-Confidence Predictions Far Away From the Training Data and How to Mitigate the Problem. | Matthias Hein, Maksym Andriushchenko, Julian Bitterwolf |
| 2019 | CVPR | Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem. | Matthias Hein, Maksym Andriushchenko, Julian Bitterwolf |
| 2019 | CVPR | Disentangling Adversarial Robustness and Generalization. | David Stutz, Matthias Hein, Bernt Schiele |
| 2019 | ICCV | Sparse and Imperceivable Adversarial Attacks. | Francesco Croce, Matthias Hein |
| 2019 | ICLR | On the loss landscape of a class of deep neural networks with no bad local valleys. | Quynh Nguyen, Mahesh Chandra Mukkamala, Matthias Hein |
| 2019 | ICML | Spectral Clustering of Signed Graphs via Matrix Power Means. | Pedro Mercado, Francesco Tudisco, Matthias Hein |
| 2018 | AISTATS | The Power Mean Laplacian for Multilayer Graph Clustering. | Pedro Mercado, Antoine Gautier, Francesco Tudisco, Matthias Hein |
| 2018 | ICLR | The loss surface and expressivity of deep convolutional neural networks. | Quynh Nguyen, Matthias Hein |
| 2018 | ICML | Optimization Landscape and Expressivity of Deep CNNs. | Quynh Nguyen, Matthias Hein |
| 2018 | ICML | Neural Networks Should Be Wide Enough to Learn Disconnected Decision Regions. | Quynh Nguyen, Mahesh Chandra Mukkamala, Matthias Hein |
| 2017 | CVPR | Simple Does It: Weakly Supervised Instance and Semantic Segmentation. | Anna Khoreva, Rodrigo Benenson, Jan Hendrik Hosang, Matthias Hein, Bernt Schiele |
| 2017 | ICML | Variants of RMSProp and Adagrad with Logarithmic Regret Bounds. | Mahesh Chandra Mukkamala, Matthias Hein |
| 2017 | ICML | The Loss Surface of Deep and Wide Neural Networks. | Quynh Nguyen, Matthias Hein |
| 2016 | CVPR | Weakly Supervised Object Boundaries. | Anna Khoreva, Rodrigo Benenson, Mohamed Omran, Matthias Hein, Bernt Schiele |
| 2016 | CVPR | Loss Functions for Top-k Error: Analysis and Insights. | Maksim Lapin, Matthias Hein, Bernt Schiele |
| 2016 | CVPR | Latent Embeddings for Zero-Shot Classification. | Yongqin Xian, Zeynep Akata, Gaurav Sharma, Quynh Nguyen, Matthias Hein, Bernt Schiele |
| 2016 | ECCV | Improved Image Boundaries for Better Video Segmentation. | Anna Khoreva, Rodrigo Benenson, Fabio Galasso, Matthias Hein, Bernt Schiele |
| 2015 | CVPR | Classifier based graph construction for video segmentation. | Anna Khoreva, Fabio Galasso, Matthias Hein, Bernt Schiele |
| 2015 | CVPR | A flexible tensor block coordinate ascent scheme for hypergraph matching. | Quynh Nguyen Ngoc, Antoine Gautier, Matthias Hein |
| 2014 | CVPR | Scalable Multitask Representation Learning for Scene Classification. | Maksim Lapin, Bernt Schiele, Matthias Hein |
| 2013 | ICML | Constrained fractional set programs and their application in local clustering and community detection. | Thomas Bhler, Syama Sundar Rangapuram, Simon Setzer, Matthias Hein |
| 2013 | WWW | Towards realistic team formation in social networks based on densest subgraphs. | Syama Sundar Rangapuram, Thomas Bhler, Matthias Hein |
| 2009 | ICML | Spectral clustering based on the graph | Thomas Bhler, Matthias Hein |
| 2007 | AAAI | Manifold Denoising as Preprocessing for Finding Natural Representations of Data. | Matthias Hein, Markus Maier |
| 2007 | ALT | Cluster Identification in Nearest-Neighbor Graphs. | Markus Maier, Matthias Hein, Ulrike von Luxburg |
| 2006 | COLT | Uniform Convergence of Adaptive Graph-Based Regularization. | Matthias Hein |
| 2005 | AISTATS | Hilbertian Metrics and Positive Definite Kernels on Probability Measures. | Matthias Hein, Olivier Bousquet |
| 2005 | COLT | From Graphs to Manifolds - Weak and Strong Pointwise Consistency of Graph Laplacians. | Matthias Hein, Jean-Yves Audibert, Ulrike von Luxburg |
| 2005 | ICML | Intrinsic dimensionality estimation of submanifolds in R | Matthias Hein, Jean-Yves Audibert |
| 2003 | COLT | Maximal Margin Classification for Metric Spaces. | Matthias Hein, Olivier Bousquet |