Mario Fritz
100 publications
18 venues
H Index 42
Affiliation
CISPA Helmholtz Center for Information Security, Saarland Informatics Campus, GermanyLinks
| Name | Venue | Year | citations |
|---|---|---|---|
DocMIA: Document-Level Membership Inference Attacks against DocVQA Models.
|
ICLR | 2025 | 1 |
| Medical Multimodal Model Stealing Attacks via Adversarial Domain Alignment.
|
AAAI | 2025 | 9 |
| Stealix: Model Stealing via Prompt Evolution.
|
ICML | 2025 | 0 |
| Pixel-level Certified Explanations via Randomized Smoothing.
|
ICML | 2025 | 5 |
| A Theory of Response Sampling in LLMs: Part Descriptive and Part Prescriptive.
|
ACL | 2025 | 0 |
| Balancing Diversity and Risk in LLM Sampling: How to Select Your Method and Parameter for Open-Ended Text Generation.
|
ACL | 2025 | 0 |
| Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?
|
ICLR | 2025 | 0 |
| Inside the Black Box: Detecting Data Leakage in Pre-Trained Language Encoders.
|
ECAI | 2024 | 2 |
| Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior Models.
|
NIPS/NeurIPS | 2024 | 5 |
| On Adversarial Training without Perturbing all Examples.
|
ICLR | 2024 | 5 |
| LLM Task Interference: An Initial Study on the Impact of Task-Switch in Conversational History.
|
EMNLP | 2024 | 19 |
| Adaptive Hierarchical Certification for Segmentation using Randomized Smoothing.
|
ICML | 2024 | 3 |
| MultiMax: Sparse and Multi-Modal Attention Learning.
|
ICML | 2024 | 2 |
| Stealthy Imitation: Reward-guided Environment-free Policy Stealing.
|
ICML | 2024 | 2 |
| Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition.
|
NIPS/NeurIPS | 2024 | 19 |
| Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation.
|
NIPS/NeurIPS | 2024 | 0 |
| B-Cos Alignment for Inherently Interpretable CNNs and Vision Transformers.
|
TPAMI | 2024 | 0 |
| Optimising for Interpretability: Convolutional Dynamic Alignment Networks.
|
TPAMI | 2023 | 0 |
| RelaxLoss: Defending Membership Inference Attacks without Losing Utility.
|
ICLR | 2022 | 57 |
| Private Set Generation with Discriminative Information.
|
NIPS/NeurIPS | 2022 | 47 |
| B-cos Networks: Alignment is All We Need for Interpretability.
|
CVPR | 2022 | 107 |
| ProgFed: Effective, Communication, and Computation Efficient Federated Learning by Progressive Training.
|
ICML | 2022 | 0 |
| Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resources.
|
CVPR | 2022 | 0 |
| Responsible Disclosure of Generative Models Using Scalable Fingerprinting.
|
ICLR | 2022 | 0 |
| Dual Contrastive Loss and Attention for GANs.
|
ICCV | 2021 | 69 |
| Euro-PVI: Pedestrian Vehicle Interactions in Dense Urban Centers.
|
CVPR | 2021 | 32 |
| Convolutional Dynamic Alignment Networks for Interpretable Classifications.
|
CVPR | 2021 | 64 |
| Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis.
|
IJCAI | 2021 | 89 |
| Hijack-GAN: Unintended-Use of Pretrained, Black-Box GANs.
|
CVPR | 2021 | 0 |
| Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data.
|
ICCV | 2021 | 0 |
| Towards Automated Testing and Robustification by Semantic Adversarial Data Generation.
|
ECCV | 2020 | 6 |
| Inclusive GAN: Improving Data and Minority Coverage in Generative Models.
|
ECCV | 2020 | 68 |
| GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators.
|
NIPS/NeurIPS | 2020 | 214 |
| Normalizing Flows With Multi-Scale Autoregressive Priors.
|
CVPR | 2020 | 19 |
| Segmentations-Leak: Membership Inference Attacks and Defenses in Semantic Image Segmentation.
|
ECCV | 2020 | 0 |
| Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editing.
|
CVPR | 2020 | 0 |
| Prediction Poisoning: Towards Defenses Against DNN Model Stealing Attacks.
|
ICLR | 2020 | 0 |
| Person Recognition in Personal Photo Collections.
|
TPAMI | 2020 | 0 |
| Time-Conditioned Action Anticipation in One Shot.
|
CVPR | 2019 | 120 |
| Knockoff Nets: Stealing Functionality of Black-Box Models.
|
CVPR | 2019 | 0 |
| Not Using the Car to See the Sidewalk - Quantifying and Controlling the Effects of Context in Classification and Segmentation.
|
CVPR | 2019 | 0 |
| Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints.
|
ICCV | 2019 | 0 |
| Deep Appearance Maps.
|
ICCV | 2019 | 0 |
| MPIIGaze: Real-World Dataset and Deep Appearance-Based Gaze Estimation.
|
TPAMI | 2019 | 0 |
| Accurate and Diverse Sampling of Sequences Based on a "Best of Many" Sample Objective.
|
CVPR | 2018 | 128 |
| Adversarial Scene Editing: Automatic Object Removal from Weak Supervision.
|
NIPS/NeurIPS | 2018 | 101 |
| Reflectance and Natural Illumination from Single-Material Specular Objects Using Deep Learning.
|
TPAMI | 2018 | 72 |
| A Hybrid Model for Identity Obfuscation by Face Replacement.
|
ECCV | 2018 | 132 |
| Diverse Conditional Image Generation by Stochastic Regression with Latent Drop-Out Codes.
|
ECCV | 2018 | 4 |
| Long-Term Image Boundary Prediction.
|
AAAI | 2018 | 0 |
| Long-Term On-Board Prediction of People in Traffic Scenes Under Uncertainty.
|
CVPR | 2018 | 0 |
| Disentangled Person Image Generation.
|
CVPR | 2018 | 0 |
| Connecting Pixels to Privacy and Utility: Automatic Redaction of Private Information in Images.
|
CVPR | 2018 | 0 |
| Natural and Effective Obfuscation by Head Inpainting.
|
CVPR | 2018 | 0 |
| Towards a Visual Privacy Advisor: Understanding and Predicting Privacy Risks in Images.
|
ICCV | 2017 | 408 |
| Adversarial Image Perturbation for Privacy Protection A Game Theory Perspective.
|
ICCV | 2017 | 167 |
| Speaking the Same Language: Matching Machine to Human Captions by Adversarial Training.
|
ICCV | 2017 | 15 |
| A Domain Based Approach to Social Relation Recognition.
|
CVPR | 2017 | 114 |
| Exploiting Saliency for Object Segmentation from Image Level Labels.
|
CVPR | 2017 | 209 |
| Visual stability prediction for robotic manipulation.
|
ICRA | 2017 | 35 |
| STD2P: RGBD Semantic Segmentation Using Spatio-Temporal Data-Driven Pooling.
|
CVPR | 2017 | 0 |
| What is Around the Camera?
|
ICCV | 2017 | 0 |
| Novel Views of Objects from a Single Image.
|
TPAMI | 2017 | 0 |
| Multi-cue Zero-Shot Learning with Strong Supervision.
|
CVPR | 2016 | 152 |
| Towards Segmenting Consumer Stereo Videos: Benchmark, Baselines and Ensembles.
|
ACCV | 2016 | 1 |
| Faceless Person Recognition: Privacy Implications in Social Media.
|
ECCV | 2016 | 170 |
| Deep Reflectance Maps.
|
CVPR | 2016 | 0 |
| See the Difference: Direct Pre-Image Reconstruction and Pose Estimation by Differentiating HOG.
|
ICCV | 2015 | 15 |
| Prediction of search targets from fixations in open-world settings.
|
CVPR | 2015 | 68 |
| Person Recognition in Personal Photo Collections.
|
ICCV | 2015 | 53 |
| Ask Your Neurons: A Neural-Based Approach to Answering Questions about Images.
|
ICCV | 2015 | 634 |
| Teaching robots the use of human tools from demonstration with non-dexterous end-effectors.
|
Humanoids | 2015 | 19 |
| Appearance-based gaze estimation in the wild.
|
CVPR | 2015 | 881 |
| A Multi-World Approach to Question Answering about Real-World Scenes based on Uncertain Input.
|
NIPS/NeurIPS | 2014 | 734 |
| Image-Based Synthesis and Re-synthesis of Viewpoints Guided by 3D Models.
|
CVPR | 2014 | 60 |
| Anytime Recognition of Objects and Scenes.
|
CVPR | 2014 | 63 |
| Sequential Bayesian Model Update under Structured Scene Prior for Semantic Road Scenes Labeling.
|
ICCV | 2013 | 28 |
| Multi-class Video Co-segmentation with a Generative Multi-video Model.
|
CVPR | 2013 | 91 |
| Semi-Supervised Learning on a Budget: Scaling Up to Large Datasets.
|
ACCV | 2012 | 11 |
| RALF: A reinforced active learning formulation for object class recognition.
|
CVPR | 2012 | 126 |
| Timely Object Recognition.
|
NIPS/NeurIPS | 2012 | 58 |
| Recognizing Materials from Virtual Examples.
|
ECCV | 2012 | 63 |
| Sparselet Models for Efficient Multiclass Object Detection.
|
ECCV | 2012 | 92 |
| The Pooled NBNN Kernel: Beyond Image-to-Class and Image-to-Image.
|
ACCV | 2012 | 22 |
| A geometric approach to robotic laundry folding.
|
IJRR | 2012 | 0 |
| The NBNN kernel.
|
ICCV | 2011 | 126 |
| A probabilistic model for recursive factorized image features.
|
CVPR | 2011 | 9 |
| Practical 3-D object detection using category and instance-level appearance models.
|
IROS | 2011 | 25 |
| Parametrized shape models for clothing.
|
ICRA | 2011 | 119 |
| Perception for the manipulation of socks.
|
IROS | 2011 | 45 |
| Size Matters: Metric Visual Search Constraints from Monocular Metadata.
|
NIPS/NeurIPS | 2010 | 18 |
| Adapting Visual Category Models to New Domains.
|
ECCV | 2010 | 3147 |
| Discriminative structure learning of hierarchical representations for object detection.
|
CVPR | 2009 | 71 |
| An Additive Latent Feature Model for Transparent Object Recognition.
|
NIPS/NeurIPS | 2009 | 82 |
| Discovery of activity patterns using topic models.
|
UbiComp | 2008 | 232 |
| Hierarchical Support Vector Random Fields: Joint Training to Combine Local and Global Features.
|
ECCV | 2008 | 42 |
| Decomposition, discovery and detection of visual categories using topic models.
|
CVPR | 2008 | 109 |
| Towards Robust Pedestrian Detection in Crowded Image Sequences.
|
CVPR | 2007 | 76 |
| Integrating Representative and Discriminative Models for Object Category Detection.
|
ICCV | 2005 | 0 |
| On the Significance of Real-World Conditions for Material Classification.
|
ECCV | 2004 | 398 |