Mario Fritz

papers

1,317

total citations

papers (19)

Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data

ICCV 2021arXiv

277

citations

GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators

NEURIPS 2020arXiv

211

citations

Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editing

CVPR 2020arXiv

181

citations

Open-Domain, Content-Based, Multi-Modal Fact-Checking of Out-of-Context Images via Online Resources

CVPR 2022arXiv

102

citations

Segmentations-Leak: Membership Inference Attacks and Defenses in Semantic Image Segmentation

ECCV 2020arXiv

citations

Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?

ICLR 2025arXiv

citations

Private Set Generation with Discriminative Information

NEURIPS 2022arXiv

citations

Euro-PVI: Pedestrian Vehicle Interactions in Dense Urban Centers

CVPR 2021arXiv

citations

Hijack-GAN: Unintended-Use of Pretrained, Black-Box GANs

CVPR 2021arXiv

citations

Normalizing Flows With Multi-Scale Autoregressive Priors

CVPR 2020arXiv

citations

Medical Multimodal Model Stealing Attacks via Adversarial Domain Alignment

AAAI 2025arXiv

citations

Stealthy Imitation: Reward-guided Environment-free Policy Stealing

ICML 2024arXiv

citations

Adaptive Hierarchical Certification for Segmentation using Randomized Smoothing

ICML 2024arXiv

citations

MultiMax: Sparse and Multi-Modal Attention Learning

ICML 2024arXiv

citations

Towards Automated Testing and Robustification by Semantic Adversarial Data Generation

ECCV 2020

citations

Mario Fritz

papers (19)

Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data

GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators

Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editing

Open-Domain, Content-Based, Multi-Modal Fact-Checking of Out-of-Context Images via Online Resources

B-Cos Networks: Alignment Is All We Need for Interpretability

Dual Contrastive Loss and Attention for GANs

Inclusive GAN: Improving Data and Minority Coverage in Generative Models

Convolutional Dynamic Alignment Networks for Interpretable Classifications

Segmentations-Leak: Membership Inference Attacks and Defenses in Semantic Image Segmentation

Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?

Private Set Generation with Discriminative Information

Euro-PVI: Pedestrian Vehicle Interactions in Dense Urban Centers

Hijack-GAN: Unintended-Use of Pretrained, Black-Box GANs

Normalizing Flows With Multi-Scale Autoregressive Priors

Medical Multimodal Model Stealing Attacks via Adversarial Domain Alignment

Stealthy Imitation: Reward-guided Environment-free Policy Stealing

Adaptive Hierarchical Certification for Segmentation using Randomized Smoothing

MultiMax: Sparse and Multi-Modal Attention Learning

Towards Automated Testing and Robustification by Semantic Adversarial Data Generation

papers (19)

Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data

GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators

Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editing

Open-Domain, Content-Based, Multi-Modal Fact-Checking of Out-of-Context Images via Online Resources

B-Cos Networks: Alignment Is All We Need for Interpretability

Dual Contrastive Loss and Attention for GANs

Inclusive GAN: Improving Data and Minority Coverage in Generative Models

Convolutional Dynamic Alignment Networks for Interpretable Classifications

Segmentations-Leak: Membership Inference Attacks and Defenses in Semantic Image Segmentation

Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?

Private Set Generation with Discriminative Information

Euro-PVI: Pedestrian Vehicle Interactions in Dense Urban Centers

Hijack-GAN: Unintended-Use of Pretrained, Black-Box GANs

Normalizing Flows With Multi-Scale Autoregressive Priors

Medical Multimodal Model Stealing Attacks via Adversarial Domain Alignment

Stealthy Imitation: Reward-guided Environment-free Policy Stealing

Adaptive Hierarchical Certification for Segmentation using Randomized Smoothing

MultiMax: Sparse and Multi-Modal Attention Learning

Towards Automated Testing and Robustification by Semantic Adversarial Data Generation