Matthias Hein

Mahalanobis++: Improving OOD Detection via Feature Normalization ICML 2025 DASH: Detection and Assessment of Systematic Hallucinations of VLMs ICCV 2025 An Interpretable N-gram Perplexity Threat Model for Large Language Model Jailbreaks ICML 2025 Mind the Detail: Uncovering Clinically Relevant Image Details in Accelerated MRI with Semantically Diverse Reconstructions MICCAI 2025 Towards Reliable Evaluation and Fast Training of Robust Semantic Segmentation Models ECCV 2024 DiG-IN: Diffusion Guidance for Investigating Networks - Uncovering Classifier Differences Neuron Visualisations and Visual Counterfactual Explanations CVPR 2024 Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models ICML 2024 Bias of Stochastic Gradient Descent or the Architecture: Disentangling the Effects of Overparameterization of Neural Networks ICML 2024 Sound Randomized Smoothing in Floating-Point Arithmetic ICLR 2023 Normalization Layers Are All That Sharpness-Aware Minimization Needs NIPS 2023 Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Models NIPS 2023 Improving l1-Certified Robustness via Randomized Smoothing by Leveraging Box Constraints ICML 2023 In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation ICML 2023 A Modern Look at the Relationship between Sharpness and Generalization ICML 2023 Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNet ICCV 2023 Certified Defences Against Adversarial Patch Attacks on Semantic Segmentation ICLR 2023 Diffusion Visual Counterfactual Explanations NIPS 2022 Provably Adversarially Robust Nearest Prototype Classifiers ICML 2022 Adversarial Robustness against Multiple and Single $l_p$-Threat Models via Quick Fine-Tuning of Robust Classifiers ICML 2022 Evaluating the Adversarial Robustness of Adaptive Test-time Defenses ICML 2022 Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantities ICML 2022 Provably Adversarially Robust Detection of Out-of-Distribution Data (Almost) for Free NIPS 2022 Sparse-RS: A Versatile Framework for Query-Efficient Sparse Black-Box Adversarial Attacks AAAI 2022 Being a Bit Frequentist Improves Bayesian Neural Networks AISTATS 2022 Learnable uncertainty under Laplace approximations UAI 2021 Relating Adversarially Robust Generalization to Flat Minima ICCV 2021 An Infinite-Feature Extension for Bayesian ReLU Nets That Fixes Their Asymptotic Overconfidence NIPS 2021 Meta-Learning the Search Distribution of Black-Box Random Search Based Adversarial Attacks NIPS 2021 Mind the Box: $l_1$-APGD for Sparse Adversarial Attacks on Image Classifiers ICML 2021 Confidence-Calibrated Adversarial Training: Generalizing to Unseen Attacks ICML 2020 Towards neural networks that provably know when they don't know ICLR 2020 Provable robustness against all adversarial $l_p$-perturbations for $p\geq 1$ ICLR 2020 Adversarial Robustness on In- and Out-Distribution Improves Explainability ECCV 2020 Certifiably Adversarially Robust Detection of Out-of-Distribution Data NIPS 2020 Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks ICML 2020 Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attack ICML 2020 Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks ICML 2020 Square Attack: a query-efficient black-box adversarial attack via random search ECCV 2020 Disentangling Adversarial Robustness and Generalization CVPR 2019 Provably robust boosted decision stumps and trees against adversarial attacks NIPS 2019 Generalized Matrix Means for Semi-Supervised Learning with Multilayer Graphs NIPS 2019 Provable Robustness of ReLU networks via Maximization of Linear Regions AISTATS 2019 Why ReLU Networks Yield High-Confidence Predictions Far Away From the Training Data and How to Mitigate the Problem CVPR 2019 Sparse and Imperceivable Adversarial Attacks ICCV 2019 On the loss landscape of a class of deep neural networks with no bad local valleys ICLR 2019 Spectral Clustering of Signed Graphs via Matrix Power Means ICML 2019 The Power Mean Laplacian for Multilayer Graph Clustering AISTATS 2018 Neural Networks Should Be Wide Enough to Learn Disconnected Decision Regions ICML 2018 Optimization Landscape and Expressivity of Deep CNNs ICML 2018 Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation NIPS 2017 Simple Does It: Weakly Supervised Instance and Semantic Segmentation CVPR 2017 The Loss Surface of Deep and Wide Neural Networks ICML 2017 Variants of RMSProp and Adagrad with Logarithmic Regret Bounds ICML 2017 Loss Functions for Top-k Error: Analysis and Insights CVPR 2016 Weakly Supervised Object Boundaries CVPR 2016 Latent Embeddings for Zero-Shot Classification CVPR 2016 Clustering Signed Networks with the Geometric Mean of Laplacians NIPS 2016 Globally Optimal Training of Generalized Polynomial Neural Networks with Nonlinear Spectral Methods NIPS 2016 Classifier Based Graph Construction for Video Segmentation CVPR 2015 Efficient Output Kernel Learning for Multiple Tasks NIPS 2015 Top-k Multiclass SVM NIPS 2015 A Flexible Tensor Block Coordinate Ascent Scheme for Hypergraph Matching CVPR 2015 Regularization-Free Estimation in Trace Regression with Symmetric Positive Semidefinite Matrices NIPS 2015 Scalable Multitask Representation Learning for Scene Classification CVPR 2014 Hitting and Commute Times in Large Random Neighborhood Graphs JMLR 2014 Tight Continuous Relaxation of the Balanced k-Cut Problem NIPS 2014 Constrained fractional set programs and their application in local clustering and community detection ICML 2013 The Total Variation on Hypergraphs - Learning on Hypergraphs Revisited NIPS 2013 Matrix factorization with binary components NIPS 2013 Constrained 1-Spectral Clustering AISTATS 2012 Sparse recovery by thresholded non-negative least squares NIPS 2011 Beyond Spectral Clustering - Tight Relaxations of Balanced Graph Cuts NIPS 2011 Getting lost in space: Large sample analysis of the resistance distance NIPS 2010 An Inverse Power Method for Nonlinear Eigenproblems with Applications in 1-Spectral Clustering and Sparse PCA NIPS 2010 Semi-supervised Regression using Hessian energy with an application to semi-supervised dimensionality reduction NIPS 2009 Robust Nonparametric Regression with Metric-Space Valued Output NIPS 2009 Influence of graph construction on graph-based clustering measures NIPS 2008 Non-parametric Regression Between Manifolds NIPS 2008 Graph Laplacians and their Convergence on Random Neighborhood Graphs JMLR 2007 Manifold Denoising NIPS 2006