Hein, Matthias

105 publications

NeurIPS 2025 Advancing Compositional Awareness in CLIP with Efficient Fine-Tuning Amit Peleg, Naman Deep Singh, Matthias Hein

ICML 2025 An Interpretable N-Gram Perplexity Threat Model for Large Language Model Jailbreaks Valentyn Boreiko, Alexander Panfilov, Vaclav Voracek, Matthias Hein, Jonas Geiping

ICCV 2025 DASH: Detection and Assessment of Systematic Hallucinations of VLMs Maximilian Augustin, Yannic Neuhaus, Matthias Hein

ICLRW 2025 Foundation Model-Based Data Selection for Dense Prediction Tasks Niclas Popp, Dan Zhang, Jan Hendrik Metzen, Matthias Hein, Lukas Schott

ICML 2025 Mahalanobis++: Improving OOD Detection via Feature Normalization Maximilian Müller, Matthias Hein

NeurIPS 2025 Robustness in Both Domains: CLIP Needs a Robust Text Encoder Elias Abad Rocamora, Christian Schlarmann, Naman Deep Singh, Yongtao Wu, Matthias Hein, Volkan Cevher

NeurIPSW 2024 A Realistic Threat Model for Large Language Model Jailbreaks Valentyn Boreiko, Alexander Panfilov, Vaclav Voracek, Matthias Hein, Jonas Geiping

ICMLW 2024 Adversarially Robust CLIP Models Induce Better (Robust) Perceptual Metrics Francesco Croce, Christian Schlarmann, Naman Deep Singh, Matthias Hein

ICML 2024 Bias of Stochastic Gradient Descent or the Architecture: Disentangling the Effects of Overparameterization of Neural Networks Amit Peleg, Matthias Hein

CVPR 2024 DiG-in: Diffusion Guidance for Investigating Networks - Uncovering Classifier Differences Neuron Visualisations and Visual Counterfactual Explanations Maximilian Augustin, Yannic Neuhaus, Matthias Hein

TMLR 2024 Feature Distillation Improves Zero-Shot Transfer from Synthetic Images Niclas Popp, Jan Hendrik Metzen, Matthias Hein

ICLRW 2024 How to Train Your VIT for OOD Detection Maximilian Müller, Matthias Hein

ICML 2024 Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models Christian Schlarmann, Naman Deep Singh, Francesco Croce, Matthias Hein

ICLRW 2024 Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models Christian Schlarmann, Naman Deep Singh, Francesco Croce, Matthias Hein

ICMLW 2024 Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models Christian Schlarmann, Naman Deep Singh, Francesco Croce, Matthias Hein

ECCV 2024 Towards Reliable Evaluation and Fast Training of Robust Semantic Segmentation Models Francesco Croce, Naman D. Singh, Matthias Hein

ICML 2023 A Modern Look at the Relationship Between Sharpness and Generalization Maksym Andriushchenko, Francesco Croce, Maximilian Müller, Matthias Hein, Nicolas Flammarion

ICLR 2023 Certified Defences Against Adversarial Patch Attacks on Semantic Segmentation Maksym Yatsura, Kaspar Sakmann, N. Grace Hua, Matthias Hein, Jan Hendrik Metzen

ICCVW 2023 Identifying Systematic Errors in Object Detectors with the SCROD Pipeline Valentyn Boreiko, Matthias Hein, Jan Hendrik Metzen

ICML 2023 Improving L1-Certified Robustness via Randomized Smoothing by Leveraging Box Constraints Vaclav Voracek, Matthias Hein

ICML 2023 In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation Julian Bitterwolf, Maximilian Müller, Matthias Hein

ICLRW 2023 In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation Julian Bitterwolf, Maximilian Mueller, Matthias Hein

NeurIPS 2023 Normalization Layers Are All That Sharpness-Aware Minimization Needs Maximilian Mueller, Tiffany Vlaar, David Rolnick, Matthias Hein

ICCVW 2023 On the Adversarial Robustness of Multi-Modal Foundation Models Christian Schlarmann, Matthias Hein

NeurIPS 2023 Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization Across Threat Models Naman Deep Singh, Francesco Croce, Matthias Hein

ICMLW 2023 Robust Semantic Segmentation: Strong Adversarial Attacks and Fast Training of Robust Models Francesco Croce, Naman Deep Singh, Matthias Hein

ICLR 2023 Sound Randomized Smoothing in Floating-Point Arithmetic Vaclav Voracek, Matthias Hein

ICCV 2023 Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNet Yannic Neuhaus, Maximilian Augustin, Valentyn Boreiko, Matthias Hein

AISTATS 2022 Being a Bit Frequentist Improves Bayesian Neural Networks Agustinus Kristiadi, Matthias Hein, Philipp Hennig

ICML 2022 Adversarial Robustness Against Multiple and Single $l_p$-Threat Models via Quick Fine-Tuning of Robust Classifiers Francesco Croce, Matthias Hein

ICML 2022 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

NeurIPSW 2022 Certified Defences Against Adversarial Patch Attacks on Semantic Segmentation Maksym Yatsura, Kaspar Sakmann, N. Grace Hua, Matthias Hein, Jan Hendrik Metzen

ICMLW 2022 Classifiers Should Do Well Even on Their Worst Classes Julian Bitterwolf, Alexander Meinke, Valentyn Boreiko, Matthias Hein

NeurIPS 2022 Diffusion Visual Counterfactual Explanations Maximilian Augustin, Valentyn Boreiko, Francesco Croce, Matthias Hein

ICML 2022 Evaluating the Adversarial Robustness of Adaptive Test-Time Defenses Francesco Croce, Sven Gowal, Thomas Brunner, Evan Shelhamer, Matthias Hein, Taylan Cemgil

ICMLW 2022 Lost in Translation: Modern Image Classifiers Still Degrade Even Under Simple Translations Leander Kurscheidt, Matthias Hein

NeurIPSW 2022 Perturbing BatchNorm and Only BatchNorm Benefits Sharpness-Aware Minimization Maximilian Mueller, Matthias Hein

NeurIPS 2022 Provably Adversarially Robust Detection of Out-of-Distribution Data (Almost) for Free Alexander Meinke, Julian Bitterwolf, Matthias Hein

ICML 2022 Provably Adversarially Robust Nearest Prototype Classifiers Václav Voráček, Matthias Hein

AAAI 2022 Sparse-RS: A Versatile Framework for Query-Efficient Sparse Black-Box Adversarial Attacks Francesco Croce, Maksym Andriushchenko, Naman D. Singh, Nicolas Flammarion, Matthias Hein

NeurIPS 2021 An Infinite-Feature Extension for Bayesian ReLU Nets That Fixes Their Asymptotic Overconfidence Agustinus Kristiadi, Matthias Hein, Philipp Hennig

UAI 2021 Learnable Uncertainty Under Laplace Approximations Agustinus Kristiadi, Matthias Hein, Philipp Hennig

NeurIPS 2021 Meta-Learning the Search Distribution of Black-Box Random Search Based Adversarial Attacks Maksym Yatsura, Jan Metzen, Matthias Hein

ICML 2021 Mind the Box: $l_1$-APGD for Sparse Adversarial Attacks on Image Classifiers Francesco Croce, Matthias Hein

ICCV 2021 Relating Adversarially Robust Generalization to Flat Minima David Stutz, Matthias Hein, Bernt Schiele

ECCV 2020 Adversarial Robustness on In- and Out-Distribution Improves Explainability Maximilian Augustin, Alexander Meinke, Matthias Hein

ICML 2020 Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks Agustinus Kristiadi, Matthias Hein, Philipp Hennig

NeurIPS 2020 Certifiably Adversarially Robust Detection of Out-of-Distribution Data Julian Bitterwolf, Alexander Meinke, Matthias Hein

ICML 2020 Confidence-Calibrated Adversarial Training: Generalizing to Unseen Attacks David Stutz, Matthias Hein, Bernt Schiele

ICML 2020 Minimally Distorted Adversarial Examples with a Fast Adaptive Boundary Attack Francesco Croce, Matthias Hein

ICLR 2020 Provable Robustness Against All Adversarial $l_p$-Perturbations for $p\geq 1$ Francesco Croce, Matthias Hein

ICML 2020 Reliable Evaluation of Adversarial Robustness with an Ensemble of Diverse Parameter-Free Attacks Francesco Croce, Matthias Hein

ECCV 2020 Square Attack: A Query-Efficient Black-Box Adversarial Attack via Random Search Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion, Matthias Hein

ICLR 2020 Towards Neural Networks That Provably Know When They Don't Know Alexander Meinke, Matthias Hein

NeurIPS 2019 Generalized Matrix Means for Semi-Supervised Learning with Multilayer Graphs Pedro Mercado, Francesco Tudisco, Matthias Hein

ICLR 2019 On the Loss Landscape of a Class of Deep Neural Networks with No Bad Local Valleys Quynh Nguyen, Mahesh Chandra Mukkamala, Matthias Hein

AISTATS 2019 Provable Robustness of ReLU Networks via Maximization of Linear Regions Francesco Croce, Maksym Andriushchenko, Matthias Hein

NeurIPS 2019 Provably Robust Boosted Decision Stumps and Trees Against Adversarial Attacks Maksym Andriushchenko, Matthias Hein

ICML 2019 Spectral Clustering of Signed Graphs via Matrix Power Means Pedro Mercado, Francesco Tudisco, Matthias Hein

CVPRW 2019 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

ICML 2018 Neural Networks Should Be Wide Enough to Learn Disconnected Decision Regions Quynh Nguyen, Mahesh Chandra Mukkamala, Matthias Hein

ICML 2018 Optimization Landscape and Expressivity of Deep CNNs Quynh Nguyen, Matthias Hein

AISTATS 2018 The Power Mean Laplacian for Multilayer Graph Clustering Pedro Mercado, Antoine Gautier, Francesco Tudisco, Matthias Hein

NeurIPS 2017 Formal Guarantees on the Robustness of a Classifier Against Adversarial Manipulation Matthias Hein, Maksym Andriushchenko

CVPR 2017 Simple Does It: Weakly Supervised Instance and Semantic Segmentation Anna Khoreva, Rodrigo Benenson, Jan Hosang, Matthias Hein, Bernt Schiele

ICML 2017 The Loss Surface of Deep and Wide Neural Networks Quynh Nguyen, Matthias Hein

ICML 2017 Variants of RMSProp and AdaGrad with Logarithmic Regret Bounds Mahesh Chandra Mukkamala, Matthias Hein

NeurIPS 2016 Clustering Signed Networks with the Geometric Mean of Laplacians Pedro Mercado, Francesco Tudisco, Matthias Hein

NeurIPS 2016 Globally Optimal Training of Generalized Polynomial Neural Networks with Nonlinear Spectral Methods Antoine Gautier, Quynh N Nguyen, Matthias Hein

ECCV 2016 Improved Image Boundaries for Better Video Segmentation Anna Khoreva, Rodrigo Benenson, Fabio Galasso, Matthias Hein, Bernt Schiele

ECCVW 2016 Improved Image Boundaries for Better Video Segmentation Anna Khoreva, Rodrigo Benenson, Fabio Galasso, Matthias Hein, Bernt Schiele

CVPR 2016 Latent Embeddings for Zero-Shot Classification Yongqin Xian, Zeynep Akata, Gaurav Sharma, Quynh Nguyen, Matthias Hein, Bernt Schiele

CVPR 2016 Loss Functions for Top-K Error: Analysis and Insights Maksim Lapin, Matthias Hein, Bernt Schiele

CVPR 2016 Weakly Supervised Object Boundaries Anna Khoreva, Rodrigo Benenson, Mohamed Omran, Matthias Hein, Bernt Schiele

CVPR 2015 A Flexible Tensor Block Coordinate Ascent Scheme for Hypergraph Matching Quynh Nguyen, Antoine Gautier, Matthias Hein

CVPR 2015 Classifier Based Graph Construction for Video Segmentation Anna Khoreva, Fabio Galasso, Matthias Hein, Bernt Schiele

NeurIPS 2015 Efficient Output Kernel Learning for Multiple Tasks Pratik Kumar Jawanpuria, Maksim Lapin, Matthias Hein, Bernt Schiele

NeurIPS 2015 Regularization-Free Estimation in Trace Regression with Symmetric Positive Semidefinite Matrices Martin Slawski, Ping Li, Matthias Hein

NeurIPS 2015 Top-K Multiclass SVM Maksim Lapin, Matthias Hein, Bernt Schiele

JMLR 2014 Hitting and Commute Times in Large Random Neighborhood Graphs Ulrike von Luxburg, Agnes Radl, Matthias Hein

CVPR 2014 Scalable Multitask Representation Learning for Scene Classification Maksim Lapin, Bernt Schiele, Matthias Hein

NeurIPS 2014 Tight Continuous Relaxation of the Balanced K-Cut Problem Syama Sundar Rangapuram, Pramod Kaushik Mudrakarta, Matthias Hein

ICML 2013 Constrained Fractional Set Programs and Their Application in Local Clustering and Community Detection Thomas Bühler, Shyam Sundar Rangapuram, Simon Setzer, Matthias Hein

NeurIPS 2013 Matrix Factorization with Binary Components Martin Slawski, Matthias Hein, Pavlo Lutsik

NeurIPS 2013 The Total Variation on Hypergraphs - Learning on Hypergraphs Revisited Matthias Hein, Simon Setzer, Leonardo Jost, Syama Sundar Rangapuram

AISTATS 2012 Constrained 1-Spectral Clustering Syama Sundar Rangapuram, Matthias Hein

NeurIPS 2011 Beyond Spectral Clustering - Tight Relaxations of Balanced Graph Cuts Matthias Hein, Simon Setzer

NeurIPS 2011 Sparse Recovery by Thresholded Non-Negative Least Squares Martin Slawski, Matthias Hein

NeurIPS 2010 An Inverse Power Method for Nonlinear Eigenproblems with Applications in 1-Spectral Clustering and Sparse PCA Matthias Hein, Thomas Bühler

NeurIPS 2010 Getting Lost in Space: Large Sample Analysis of the Resistance Distance Ulrike V. Luxburg, Agnes Radl, Matthias Hein

NeurIPS 2009 Robust Nonparametric Regression with Metric-Space Valued Output Matthias Hein

NeurIPS 2009 Semi-Supervised Regression Using Hessian Energy with an Application to Semi-Supervised Dimensionality Reduction Kwang I. Kim, Florian Steinke, Matthias Hein

ICML 2009 Spectral Clustering Based on the Graph P-Laplacian Thomas Bühler, Matthias Hein

NeurIPS 2008 Influence of Graph Construction on Graph-Based Clustering Measures Markus Maier, Ulrike V. Luxburg, Matthias Hein

NeurIPS 2008 Non-Parametric Regression Between Manifolds Florian Steinke, Matthias Hein

ALT 2007 Cluster Identification in Nearest-Neighbor Graphs Markus Maier, Matthias Hein, Ulrike von Luxburg

JMLR 2007 Graph Laplacians and Their Convergence on Random Neighborhood Graphs Matthias Hein, Jean-Yves Audibert, Ulrike von Luxburg

AAAI 2007 Manifold Denoising as Preprocessing for Finding Natural Representations of Data Matthias Hein, Markus Maier

NeurIPS 2006 Manifold Denoising Matthias Hein, Markus Maier

COLT 2006 Uniform Convergence of Adaptive Graph-Based Regularization Matthias Hein

COLT 2005 From Graphs to Manifolds - Weak and Strong Pointwise Consistency of Graph Laplacians Matthias Hein, Jean-Yves Audibert, Ulrike von Luxburg

AISTATS 2005 Hilbertian Metrics and Positive Definite Kernels on Probability Measures Matthias Hein, Olivier Bousquet

ICML 2005 Intrinsic Dimensionality Estimation of Submanifolds in Rd Matthias Hein, Jean-Yves Audibert

COLT 2003 Maximal Margin Classification for Metric Spaces Matthias Hein, Olivier Bousquet

NeurIPS 2003 Measure Based Regularization Olivier Bousquet, Olivier Chapelle, Matthias Hein