• HOME
  • GROUP
  • RESEARCH
  • TEACHING
  • CONTACT

Mario Fritz – CISPA Helmholtz Center for Information Security

Mario Fritz – CISPA Helmholtz Center for Information Security

Prof. Dr. Mario Fritz


Faculty
CISPA Helmholtz Center for Information Security

Professor
Saarland University

Fellow
European Laboratory for Learning and Intelligent Systems (ELLIS)


Google Scholar 

Semantic Scholar


We are looking for PhD students and Post-Docs! Please get in touch.

My group is working on Trustworthy Information Processing with a focus on the intersection of AI & Machine Learning with Security & Privacy.


Recent projects and initiatives related to trustworthy AI/ML, health, privacy:

  • Coordinator and PI: European Lighthouse on Secure and Safe AI (ELSA)
  • Leading Scientist: Helmholtz Medical Security, Privacy, and AI Research Center (HMSP)
  • Coordinator and PI: Trustworthy Federated Data Analytics Project (TFDA)
  • Coordinator and PI: Protecting Genetic Data with Synthetic Cohorts from Deep Generative Models (PRO-GENE-GEN)
  • PI: Integrated Early Warning System for Local Recognition, Prevention, and Control for Epidemic Outbreaks (LOKI)
  • Partner-PI: The German Human Genome-Phenome Archive (GHGA)
  • Member of working group in “Forum Gesundheit” of BMBF: “AG Nutzbarmachung digitaler Daten für KI-Entwicklungen in der Gesundheitsforschung”

Recent work on DeepFake detecting, misinformation, attribution,and responsible disclosure:

  • Usenix’23: UnGANable: Defending Against GAN-based Face Manipulation
  • ArXiv’22: Fact-Saboteurs: A Taxonomy of Evidence Manipulation Attacks against Fact-Verification Systems
  • CVPR’22: Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resources
  • ICLR’22: Responsible Disclosure of Generative Models Using Scalable Fingerprinting
  • ICCV’21: Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data
  • S&P’21: Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hiding
  • IJCAI’21: Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis
  • CVPR’21: Hijack-GAN: Unintended-Use of Pretrained, Black-Box GANs
  • ICCV’19: Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints

Recent publications:

  • Usenix’23: UnGANable: Defending Against GAN-based Face Manipulation
  • NeurIPS’22: Private Set Generation with Discriminative Information
  • ICML’22: ProgFed: Effective, Communication, and Computation Efficient Federated Learning by Progressive Training
  • CVPR’22: Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resources
  • CVPR’22: B-cos Networks: Alignment is All We Need for Interpretability
  • CHIL’22: Practical Challenges in Differentially-Private Federated Survival Analysis of Medical Data
  • ICLR’22: Responsible Disclosure of Generative Models Using Scalable Fingerprinting
  • ICLR’22: RelaxLoss: Defending Membership Inference Attacks without Losing Utility
  • Usenix’22: ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models
  • PETS’22: Understanding Utility and Privacy of Demographic Data in Education Technology by Causal Analysis and Adversarial-Censoring
  • IJCV’21: Semantic Bottlenecks: Quantifying and Improving Inspectability of Deep Representations
  • CCS-W’21: Differential Privacy Defenses and Sampling Attacks for Membership Inference
  • CCS-W’21: “What’s in the box?!”: Deflecting Adversarial Attacks by Randomly Deploying Adversarially-Disjoint Models
  • PKDD-W’21: IReEn: Reverse-Engineering of Black-Box Functions via Iterative Neural Program Synthesis
  • PKDD-W’21: SampleFix: Learning to Generate Functionally Diverse Fixes
  • ICCV’21: Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data
  • ICCV’21: Dual Contrastive Loss and Attention for GANs
  • EXCLI’21: Privacy Considerations for Sharing Genomics Data
  • IJCAI’21: Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis
  • S&P’21: Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hiding
  • CVPR’21: Hijack-GAN: Unintended-Use of Pretrained, Black-Box GANs
  • CVPR’21: Convolutional Dynamic Alignment Networks for Interpretable Classifications
  • CVPR’21: Euro-PVI: Pedestrian Vehicle Interactions in Dense Urban Centers
  • CVPR-W’21: MLCapsule: Guarded Offline Deployment of Machine Learning as a Service
  • CVPR-W’21: InfoScrub: Towards Attribute Privacy by Targeted Obfuscation
  • WACV’21: Future Moment Assessment for Action Query

News, talks, events:

  • Talk at Deutscher EDV Gerichtstag
  • Talk at AI, Neuroscience and Hardware: From Neural to Artificial Systems and Back Again
  • Scientific Advisory Board: Bosch AIShield
  • Steering Board: Helmholtz.AI
  • Recent program committees: ICML’21, NeurIPS’21, S&P’22, EuroS&P’22, CVPR’22 (AC); CCS’22
  • Runner-up Inria/CNIL Privacy Protection Prize 2020
    S&P’20 paper: “Automatically Detecting Bystanders in Photos to Reduce Privacy Risks”
  • Co-Organizers of ICLR’21 Workshop on “Synthetic Data Generation – Quality, Privacy, Bias”
  • Co-Organizers of CVPR’21 Workshop on “QuoVadis: Interdisciplinary, Socio-Technical Workshop on the Future of Computer Vision and Pattern Recognition (QuoVadis-CVPR)”
  • Co-Organizers of CVPR’21 Workshop on “Causality in Vision”
  • Founding member of Saarbrücken Artificial Intelligence & Machine Learning (SAM) unit of the European Laboratory of Learning and Intelligent Systems (ELLIS)
  • Lecturer at Digital CISPA Summer School 2020
  • Co-Organizer of Third International Workshop on The Bright and Dark Sides of Computer Vision: Challenges and Opportunities for Privacy and Security (CV-COPS) at ECCV 2020
  • Co-Organizer: 4. ACM Symposium on Computer Science in Cars: Future Challenges in Artificial Intelligence & Security for Autonomous Vehicles CSCS’20
  • Keynote at Workshop Machine Learning for Cybersecurity, ECMLPKDD’19
  • Talk at Cyber Defense Campus (CYD) Conference on Artificial Intelligence in Defence and Security
  • Co-Organizer of Second International Workshop on The Bright and Dark Sides of Computer Vision: Challenges and Opportunities for Privacy and Security (CV-COPS) at CVPR 2019
  • Co-Organizer: 3. ACM Symposium on Computer Science in Cars: Future Challenges in Artificial Intelligence & Security for Autonomous Vehicles CSCS’19
  • Leading scientist at new Helmholtz Medical Security and Privacy Research Center
  • Member of ACM Technical Policy Committee Europe
  • Mateusz Malinowski received the DAGM MVTec dissertation award as well as the Dr.-Eduard-Martin award for his PhD
  • Associate Editor for IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

2011 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022

Show all

2020

Journal Articles

 Person Recognition in Personal Photo Collections

Seong Joon Oh; Rodrigo Benenson; Mario Fritz; Bernt Schiele

Person Recognition in Personal Photo Collections Journal Article

In: IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2020.

Links | BibTeX | Tags: 2020

@article{oh20tpami,
title = { Person Recognition in Personal Photo Collections },
author = {Seong Joon Oh and Rodrigo Benenson and Mario Fritz and Bernt Schiele},
url = {https://ieeexplore.ieee.org/document/8519337?source=authoralert},
year = {2020},
date = {2020-01-01},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
keywords = {2020},
pubstate = {published},
tppubtype = {article}
}

Close

  • https://ieeexplore.ieee.org/document/8519337?source=authoralert

Close

Deep Gaze Pooling: Inferring and Visually Decoding Search Intents From Human Gaze Fixations

Hosnieh Sattar; Mario Fritz; Andreas Bulling

Deep Gaze Pooling: Inferring and Visually Decoding Search Intents From Human Gaze Fixations Journal Article

In: Neurocomputing, vol. 387, pp. 369–382, 2020.

Links | BibTeX | Tags: 2020

@article{sattar20_neurocomp,
title = {Deep Gaze Pooling: Inferring and Visually Decoding Search Intents From Human Gaze Fixations},
author = {Hosnieh Sattar and Mario Fritz and Andreas Bulling},
url = {https://www.perceptualui.org/publications/sattar20_neurocomp.pdf},
doi = {10.1016/j.neucom.2020.01.028},
year = {2020},
date = {2020-01-01},
journal = {Neurocomputing},
volume = {387},
pages = {369–382},
keywords = {2020},
pubstate = {published},
tppubtype = {article}
}

Close

  • https://www.perceptualui.org/publications/sattar20_neurocomp.pdf
  • doi:10.1016/j.neucom.2020.01.028

Close

Inproceedings

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

Dingfan Chen; Tribhuvanesh Orekondy; Mario Fritz

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

In: Neural Information Processing Systems (NeurIPS), 2020.

Links | BibTeX | Tags: 2020

@inproceedings{neurips20chen,
title = {GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators},
author = {Dingfan Chen and Tribhuvanesh Orekondy and Mario Fritz},
url = {https://arxiv.org/abs/2006.08265
https://arxiv.org/pdf/2006.08265.pdf},
year = {2020},
date = {2020-12-06},
booktitle = {Neural Information Processing Systems (NeurIPS)},
keywords = {2020},
pubstate = {published},
tppubtype = {inproceedings}
}

Close

  • https://arxiv.org/abs/2006.08265
  • https://arxiv.org/pdf/2006.08265.pdf

Close

GAN-Leaks: A Taxonomy of Membership Inference Attacks against GANs

Dingfan Chen; Ning Yu; Yang Zhang; Mario Fritz

GAN-Leaks: A Taxonomy of Membership Inference Attacks against GANs Inproceedings

In: ACM Conference on Computer and Communications Security (CCS) , 2020.

Links | BibTeX | Tags: 2020

@inproceedings{chen20ccs,
title = {GAN-Leaks: A Taxonomy of Membership Inference Attacks against GANs},
author = {Dingfan Chen and Ning Yu and Yang Zhang and Mario Fritz},
url = {https://arxiv.org/abs/1909.03935
https://arxiv.org/pdf/1909.03935.pdf},
year = {2020},
date = {2020-11-09},
booktitle = {ACM Conference on Computer and Communications Security (CCS) },
keywords = {2020},
pubstate = {published},
tppubtype = {inproceedings}
}

Close

  • https://arxiv.org/abs/1909.03935
  • https://arxiv.org/pdf/1909.03935.pdf

Close

VisualPhishNet: Zero-Day Phishing Website Detection by Visual Similarity

Sahar Abdelnabi; Katharina Krombholz; Mario Fritz

VisualPhishNet: Zero-Day Phishing Website Detection by Visual Similarity Inproceedings

In: ACM Conference on Computer and Communications Security (CCS) , 2020.

Links | BibTeX | Tags: 2020

@inproceedings{abdelnabi20ccs,
title = {VisualPhishNet: Zero-Day Phishing Website Detection by Visual Similarity},
author = {Sahar Abdelnabi and Katharina Krombholz and Mario Fritz},
url = {https://arxiv.org/abs/1909.00300
https://arxiv.org/pdf/1909.00300.pdf},
year = {2020},
date = {2020-11-09},
booktitle = {ACM Conference on Computer and Communications Security (CCS) },
keywords = {2020},
pubstate = {published},
tppubtype = {inproceedings}
}

Close

  • https://arxiv.org/abs/1909.00300
  • https://arxiv.org/pdf/1909.00300.pdf

Close

Haar Wavelet based Block Autoregressive Flows for Trajectories

Apratim Bhattacharyya; Christoph-Nikolas Straehle; Mario Fritz; Bernt Schiele

Haar Wavelet based Block Autoregressive Flows for Trajectories Inproceedings

In: German Conference on Pattern Recognition (GCPR), 2020.

Links | BibTeX | Tags: 2020

@inproceedings{gcpr20bhattacharyya,
title = {Haar Wavelet based Block Autoregressive Flows for Trajectories},
author = {Apratim Bhattacharyya and Christoph-Nikolas Straehle and Mario Fritz and Bernt Schiele},
url = {https://unitc-my.sharepoint.com/personal/iigaf01_cloud_uni-tuebingen_de/Documents/gcpr_vmv_vcbm/gcpr/preprints/Apratim_Bhattacharyy_gcpr_0067_v01.pdf?originalPath=aHR0cHM6Ly91bml0Yy1teS5zaGFyZXBvaW50LmNvbS86YjovZy9wZXJzb25hbC9paWdhZjAxX2Nsb3VkX3VuaS10dWViaW5nZW5fZGUvRVpsOHdqUWRjdXhBa2VpTEo3NmNET3dCd2FQZjZpY2xUSTUxNkJ6VjdmbUV1dz9ydGltZT03YzZyZUgxbzJFZw
https://arxiv.org/abs/2009.09878
https://arxiv.org/pdf/2009.09878.pdf},
year = {2020},
date = {2020-09-30},
booktitle = {German Conference on Pattern Recognition (GCPR)},
keywords = {2020},
pubstate = {published},
tppubtype = {inproceedings}
}

Close

  • https://unitc-my.sharepoint.com/personal/iigaf01_cloud_uni-tuebingen_de/Document[...]
  • https://arxiv.org/abs/2009.09878
  • https://arxiv.org/pdf/2009.09878.pdf

Close

Long-Tailed Recognition Using Class-Balanced Experts

Saurabh Sharma; Ning Yu; Mario Fritz; Bernt Schiele

Long-Tailed Recognition Using Class-Balanced Experts Inproceedings

In: German Conference on Pattern Recognition (GCPR), 2020.

Links | BibTeX | Tags: 2020

@inproceedings{gcpr20sharma,
title = {Long-Tailed Recognition Using Class-Balanced Experts},
author = {Saurabh Sharma and Ning Yu and Mario Fritz and Bernt Schiele},
url = {https://arxiv.org/abs/2004.03706
https://arxiv.org/pdf/2004.03706.pdf},
year = {2020},
date = {2020-09-29},
booktitle = {German Conference on Pattern Recognition (GCPR)},
keywords = {2020},
pubstate = {published},
tppubtype = {inproceedings}
}

Close

  • https://arxiv.org/abs/2004.03706
  • https://arxiv.org/pdf/2004.03706.pdf

Close

Semantic Bottlenecks: Quantifying & Improving Inspectability of Deep Representations

Max Losch; Mario Fritz; Bernt Schiele

Semantic Bottlenecks: Quantifying & Improving Inspectability of Deep Representations Inproceedings

In: German Conference on Patter Recognition (GCPR), 2020.

Links | BibTeX | Tags: 2020

@inproceedings{gcpr20losch,
title = {Semantic Bottlenecks: Quantifying & Improving Inspectability of Deep Representations},
author = {Max Losch and Mario Fritz and Bernt Schiele},
url = {https://unitc-my.sharepoint.com/personal/iigaf01_cloud_uni-tuebingen_de/Documents/gcpr_vmv_vcbm/gcpr/preprints/gcpr_0028_v01.pdf?originalPath=aHR0cHM6Ly91bml0Yy1teS5zaGFyZXBvaW50LmNvbS86YjovZy9wZXJzb25hbC9paWdhZjAxX2Nsb3VkX3VuaS10dWViaW5nZW5fZGUvRVhYM0ZsVEczS2RGaDZ3aDc4T1FBQWNCSGE5VmJwNWFFeDFZUURiSmZER21rdz9ydGltZT1WR052OUgxbzJFZw},
year = {2020},
date = {2020-09-29},
booktitle = {German Conference on Patter Recognition (GCPR)},
keywords = {2020},
pubstate = {published},
tppubtype = {inproceedings}
}

Close

  • https://unitc-my.sharepoint.com/personal/iigaf01_cloud_uni-tuebingen_de/Document[...]

Close

Towards Automated Testing and Robustification by Semantic Adversarial Data Generation

Rakshith Shetty; Mario Fritz; Bernt Schiele

Towards Automated Testing and Robustification by Semantic Adversarial Data Generation Inproceedings

In: European Conference on Computer Vision (ECCV), 2020.

Links | BibTeX | Tags: 2020

@inproceedings{shetty20eccv,
title = {Towards Automated Testing and Robustification by Semantic Adversarial Data Generation},
author = {Rakshith Shetty and Mario Fritz and Bernt Schiele},
url = {https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123470477.pdf},
year = {2020},
date = {2020-08-23},
booktitle = {European Conference on Computer Vision (ECCV)},
keywords = {2020},
pubstate = {published},
tppubtype = {inproceedings}
}

Close

  • https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123470477.pdf

Close

Inclusive GAN: Improving Data and Minority Coverage in Generative Models

Ning Yu; Ke Li; Peng Zhou; Jitendra Malik; Larry S. Davis; Mario Fritz

Inclusive GAN: Improving Data and Minority Coverage in Generative Models Inproceedings

In: European Conference on Computer Vision (ECCV), 2020.

Links | BibTeX | Tags: 2020

@inproceedings{yu20eccv,
title = {Inclusive GAN: Improving Data and Minority Coverage in Generative Models},
author = {Ning Yu and Ke Li and Peng Zhou and Jitendra Malik and Larry S. Davis and Mario Fritz},
url = {https://arxiv.org/abs/2004.03355
https://arxiv.org/pdf/2004.03355.pdf},
year = {2020},
date = {2020-08-23},
booktitle = {European Conference on Computer Vision (ECCV)},
keywords = {2020},
pubstate = {published},
tppubtype = {inproceedings}
}

Close

  • https://arxiv.org/abs/2004.03355
  • https://arxiv.org/pdf/2004.03355.pdf

Close

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

Yang He; Shadi Rahimian; Bernt Schiele; Mario Fritz

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

In: European Conference on Computer Vision (ECCV), 2020.

Links | BibTeX | Tags: 2020

@inproceedings{he20eccv,
title = {Segmentations-Leak: Membership Inference Attacks and Defenses in Semantic Image Segmentation},
author = {Yang He and Shadi Rahimian and Bernt Schiele and Mario Fritz},
url = {https://github.com/SSAW14/segmentation_membership_inference
https://arxiv.org/abs/1912.09685
https://arxiv.org/pdf/1912.09685.pdf},
year = {2020},
date = {2020-08-23},
booktitle = {European Conference on Computer Vision (ECCV)},
keywords = {2020},
pubstate = {published},
tppubtype = {inproceedings}
}

Close

  • https://github.com/SSAW14/segmentation_membership_inference
  • https://arxiv.org/abs/1912.09685
  • https://arxiv.org/pdf/1912.09685.pdf

Close

Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learning

Ahmed Salem; Apratim Bhattacharyya; Michael Backes; Mario Fritz; Yang Zhang

Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learning Inproceedings

In: USENIX Security Symposium (USENIX Security 20), 2020.

Links | BibTeX | Tags: 2020

@inproceedings{salem20usenix,
title = {Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learning},
author = {Ahmed Salem and Apratim Bhattacharyya and Michael Backes and Mario Fritz and Yang Zhang},
url = {preliminary version:
https://arxiv.org/abs/1904.01067
https://arxiv.org/pdf/1904.01067.pdf},
year = {2020},
date = {2020-08-12},
booktitle = {USENIX Security Symposium (USENIX Security 20)},
keywords = {2020},
pubstate = {published},
tppubtype = {inproceedings}
}

Close

  • preliminary version:
  • https://arxiv.org/abs/1904.01067
  • https://arxiv.org/pdf/1904.01067.pdf

Close

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

Vedika Agarwal; Rakshith Shetty; Mario Fritz

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

In: IEEE Conference on Computer Vision and Pattern Recognition, 2020.

Links | BibTeX | Tags: 2020

@inproceedings{agarwal20cvpr,
title = {Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editing},
author = {Vedika Agarwal and Rakshith Shetty and Mario Fritz
},
url = {preliminary version:
https://arxiv.org/abs/1912.07538
https://arxiv.org/pdf/1912.07538.pdf
https://rakshithshetty.github.io/CausalVQA/},
year = {2020},
date = {2020-06-15},
booktitle = {IEEE Conference on Computer Vision and Pattern Recognition},
keywords = {2020},
pubstate = {published},
tppubtype = {inproceedings}
}

Close

  • preliminary version:
  • https://arxiv.org/abs/1912.07538
  • https://arxiv.org/pdf/1912.07538.pdf
  • https://rakshithshetty.github.io/CausalVQA/

Close

Normalizing Flows with Multi-scale Autoregressive Priors

Apratim Bhattacharyya; Shweta Mahajan; Mario Fritz; Bernt Schiele; Stefan Roth

Normalizing Flows with Multi-scale Autoregressive Priors Inproceedings

In: IEEE Conference on Computer Vision and Pattern Recognition, 2020.

Links | BibTeX | Tags: 2020

@inproceedings{apratim20cvpr,
title = {Normalizing Flows with Multi-scale Autoregressive Priors},
author = {Apratim Bhattacharyya and Shweta Mahajan and Mario Fritz and Bernt Schiele and Stefan Roth},
url = {https://arxiv.org/abs/2004.03891
https://arxiv.org/pdf/2004.03891.pdf
https://github.com/visinf/mar-scf},
year = {2020},
date = {2020-06-14},
booktitle = {IEEE Conference on Computer Vision and Pattern Recognition},
keywords = {2020},
pubstate = {published},
tppubtype = {inproceedings}
}

Close

  • https://arxiv.org/abs/2004.03891
  • https://arxiv.org/pdf/2004.03891.pdf
  • https://github.com/visinf/mar-scf

Close

Automatically Detecting Bystanders in Photos to Reduce Privacy Risks

Rakibul Hasan; David Crandall; Mario Fritz; Apu Kapadia

Automatically Detecting Bystanders in Photos to Reduce Privacy Risks Inproceedings

In: IEEE Symposium on Security and Privacy (S&P), 2020.

Links | BibTeX | Tags: 2020

@inproceedings{hasan20sp,
title = {Automatically Detecting Bystanders in Photos to Reduce Privacy Risks},
author = {Rakibul Hasan and David Crandall and Mario Fritz and Apu Kapadia},
url = {https://homes.luddy.indiana.edu/kapadia/papers/hasan-oakland-20-preprint.pdf
https://www.youtube.com/watch?v=TDupeMj0bXg
https://www.youtube.com/watch?v=uwKM_S8RpTQ
},
year = {2020},
date = {2020-05-18},
booktitle = {IEEE Symposium on Security and Privacy (S&P)},
keywords = {2020},
pubstate = {published},
tppubtype = {inproceedings}
}

Close

  • https://homes.luddy.indiana.edu/kapadia/papers/hasan-oakland-20-preprint.pdf
  • https://www.youtube.com/watch?v=TDupeMj0bXg
  • https://www.youtube.com/watch?v=uwKM_S8RpTQ

Close

Technical Reports

CosSGD: Nonlinear Quantization for Communication-efficient Federated Learning

Yang He; Maximilian Zenk; Mario Fritz

CosSGD: Nonlinear Quantization for Communication-efficient Federated Learning Technical Report

arXiv:2012.08241 , 2020.

Links | BibTeX | Tags: 2020

@techreport{yang20arxiv,
title = {CosSGD: Nonlinear Quantization for Communication-efficient Federated Learning},
author = {Yang He and Maximilian Zenk and Mario Fritz},
url = {https://arxiv.org/abs/2012.08241
https://arxiv.org/pdf/2012.08241.pdf},
year = {2020},
date = {2020-12-15},
type = {arXiv:2012.08241 },
keywords = {2020},
pubstate = {published},
tppubtype = {techreport}
}

Close

  • https://arxiv.org/abs/2012.08241
  • https://arxiv.org/pdf/2012.08241.pdf

Close

Responsible Disclosure of Generative Models Using Scalable Fingerprinting

Ning Yu; Vladislav Skripniuk; Dingfan Chen; Larry Davis; Mario Fritz

Responsible Disclosure of Generative Models Using Scalable Fingerprinting Technical Report

arXiv:2012.08726 , 2020.

Links | BibTeX | Tags: 2020

@techreport{yu20arxiv,
title = {Responsible Disclosure of Generative Models Using Scalable Fingerprinting},
author = {Ning Yu and Vladislav Skripniuk and Dingfan Chen and Larry Davis and Mario Fritz},
url = {https://arxiv.org/abs/2012.08726
https://arxiv.org/pdf/2012.08726.pdf},
year = {2020},
date = {2020-12-15},
type = {arXiv:2012.08726 },
keywords = {2020},
pubstate = {published},
tppubtype = {techreport}
}

Close

  • https://arxiv.org/abs/2012.08726
  • https://arxiv.org/pdf/2012.08726.pdf

Close

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

Hui-Po Wang; Ning Yu; Mario Fritz

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

arXiv:2011.14107 , 2020.

Links | BibTeX | Tags: 2020

@techreport{po20arxiv,
title = {Hijack-GAN: Unintended-Use of Pretrained, Black-Box GANs},
author = {Hui-Po Wang and Ning Yu and Mario Fritz},
url = {https://arxiv.org/abs/2011.14107
https://arxiv.org/pdf/2011.14107.pdf},
year = {2020},
date = {2020-11-28},
type = {arXiv:2011.14107 },
keywords = {2020},
pubstate = {published},
tppubtype = {techreport}
}

Close

  • https://arxiv.org/abs/2011.14107
  • https://arxiv.org/pdf/2011.14107.pdf

Close

Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hiding

Sahar Abdelnabi; Mario Fritz

Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hiding Technical Report

arXiv:2009.03015 [cs.CR], 2020.

Links | BibTeX | Tags: 2020

@techreport{abdelnabi20arxiv,
title = {Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hiding},
author = {Sahar Abdelnabi and Mario Fritz},
url = {https://arxiv.org/abs/2009.03015
https://arxiv.org/pdf/2009.03015.pdf},
year = {2020},
date = {2020-09-07},
type = {arXiv:2009.03015 [cs.CR]},
keywords = {2020},
pubstate = {published},
tppubtype = {techreport}
}

Close

  • https://arxiv.org/abs/2009.03015
  • https://arxiv.org/pdf/2009.03015.pdf

Close

Black-Box Watermarking for Generative Adversarial Networks

Vladislav Skripniuk; Ning Yu; Sahar Abdelnabi; Mario Fritz

Black-Box Watermarking for Generative Adversarial Networks Technical Report

arXiv:2007.08457, 2020.

Links | BibTeX | Tags: 2020

@techreport{arxiv20skripniuk,
title = {Black-Box Watermarking for Generative Adversarial Networks},
author = {Vladislav Skripniuk and Ning Yu and Sahar Abdelnabi and Mario Fritz},
url = {https://arxiv.org/abs/2007.08457
https://arxiv.org/pdf/2007.08457.pdf},
year = {2020},
date = {2020-07-17},
type = {arXiv:2007.08457},
keywords = {2020},
pubstate = {published},
tppubtype = {techreport}
}

Close

  • https://arxiv.org/abs/2007.08457
  • https://arxiv.org/pdf/2007.08457.pdf

Close

IReEn: Iterative Reverse-Engineering of Black-Box Functions via Neural Program Synthesis

Hossein Hajipour; Mateusz Malinowski; Mario Fritz

IReEn: Iterative Reverse-Engineering of Black-Box Functions via Neural Program Synthesis Technical Report

arXiv:2006.10720, 2020.

Links | BibTeX | Tags: 2020

@techreport{hajipour20arxiv,
title = {IReEn: Iterative Reverse-Engineering of Black-Box Functions via Neural Program Synthesis},
author = {Hossein Hajipour and Mateusz Malinowski and Mario Fritz},
url = {https://arxiv.org/abs/2006.10720
https://arxiv.org/pdf/2006.10720.pdf},
year = {2020},
date = {2020-06-18},
type = {arXiv:2006.10720},
keywords = {2020},
pubstate = {published},
tppubtype = {techreport}
}

Close

  • https://arxiv.org/abs/2006.10720
  • https://arxiv.org/pdf/2006.10720.pdf

Close

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

Dingfan Chen; Tribhuvanesh Orekondy; Mario Fritz

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

arXiv:2006.08265 , 2020.

Links | BibTeX | Tags: 2020

@techreport{chen20arxiv,
title = {GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators},
author = {Dingfan Chen and Tribhuvanesh Orekondy and Mario Fritz},
url = {https://arxiv.org/abs/2006.08265
https://arxiv.org/pdf/2006.08265.pdf},
year = {2020},
date = {2020-06-16},
type = {arXiv:2006.08265 },
keywords = {2020},
pubstate = {published},
tppubtype = {techreport}
}

Close

  • https://arxiv.org/abs/2006.08265
  • https://arxiv.org/pdf/2006.08265.pdf

Close

 Inclusive GAN: Improving Data and Minority Coverage in Generative Models

Ning Yu; Ke Li; Peng Zhou; Jitendra Malik; Larry Davis; Mario Fritz

Inclusive GAN: Improving Data and Minority Coverage in Generative Models Technical Report

2020.

Links | BibTeX | Tags: 2020

@techreport{ning20arxiv,
title = { Inclusive GAN: Improving Data and Minority Coverage in Generative Models },
author = {Ning Yu and Ke Li and Peng Zhou and Jitendra Malik and Larry Davis and Mario Fritz},
url = {https://arxiv.org/abs/2004.03355
https://arxiv.org/pdf/2004.03355.pdf},
year = {2020},
date = {2020-04-07},
keywords = {2020},
pubstate = {published},
tppubtype = {techreport}
}

Close

  • https://arxiv.org/abs/2004.03355
  • https://arxiv.org/pdf/2004.03355.pdf

Close

Long-Tailed Recognition Using Class-Balanced Experts

Saurabh Sharma; Ning Yu; Mario Fritz; Bernt Schiele

Long-Tailed Recognition Using Class-Balanced Experts Technical Report

arXiv:2004.03706 , 2020.

Links | BibTeX | Tags: 2020

@techreport{sharma20arxiv,
title = {Long-Tailed Recognition Using Class-Balanced Experts},
author = {Saurabh Sharma and Ning Yu and Mario Fritz and Bernt Schiele},
url = {https://arxiv.org/abs/2004.03706
https://arxiv.org/pdf/2004.03706.pdf},
year = {2020},
date = {2020-04-07},
type = {arXiv:2004.03706 },
keywords = {2020},
pubstate = {published},
tppubtype = {techreport}
}

Close

  • https://arxiv.org/abs/2004.03706
  • https://arxiv.org/pdf/2004.03706.pdf

Close

Workshops

SampleFix: Learning to Correct Programs by Sampling Diverse Fixes

Hossein Hajipour; Apratim Bhattacharyya; Mario Fritz

SampleFix: Learning to Correct Programs by Sampling Diverse Fixes Workshop

NeurIPS Workshop on Computer-Assisted Programming, 2020.

Links | BibTeX | Tags: 2019, 2020

@workshop{hajipour20neuripscap,
title = {SampleFix: Learning to Correct Programs by Sampling Diverse Fixes},
author = {Hossein Hajipour and Apratim Bhattacharyya and Mario Fritz},
url = {https://arxiv.org/abs/1906.10502
https://arxiv.org/pdf/1906.10502.pdf},
year = {2020},
date = {2020-12-06},
urldate = {2020-12-06},
booktitle = {NeurIPS Workshop on Computer-Assisted Programming},
keywords = {2019, 2020},
pubstate = {published},
tppubtype = {workshop}
}

Close

  • https://arxiv.org/abs/1906.10502
  • https://arxiv.org/pdf/1906.10502.pdf

Close

IReEn: Iterative Reverse-Engineering of Black-Box Functions via Neural Program Synthesis

Hossein Hajipour; Mateusz Malinowski; Mario Fritz

IReEn: Iterative Reverse-Engineering of Black-Box Functions via Neural Program Synthesis Workshop

NeurIPS Workshop on Computer-Assisted Programming, 2020.

Links | BibTeX | Tags: 2020

@workshop{neuripscap20hajipour,
title = {IReEn: Iterative Reverse-Engineering of Black-Box Functions via Neural Program Synthesis},
author = {Hossein Hajipour and Mateusz Malinowski and Mario Fritz},
url = {https://arxiv.org/abs/2006.10720
https://arxiv.org/pdf/2006.10720.pdf},
year = {2020},
date = {2020-12-06},
booktitle = {NeurIPS Workshop on Computer-Assisted Programming},
keywords = {2020},
pubstate = {published},
tppubtype = {workshop}
}

Close

  • https://arxiv.org/abs/2006.10720
  • https://arxiv.org/pdf/2006.10720.pdf

Close

Haar Wavelet based Block Autoregressive Flows for Trajectories

Apratim Bhattacharyya; Christoph-Nikolas Straehle; Mario Fritz; Bernt Schiele

Haar Wavelet based Block Autoregressive Flows for Trajectories Workshop

NeurIPS Workshop on Machine Learning for Autonomous Driving, 2020.

Links | BibTeX | Tags: 2020

@workshop{neuripsml4ad20apratim,
title = {Haar Wavelet based Block Autoregressive Flows for Trajectories},
author = {Apratim Bhattacharyya and Christoph-Nikolas Straehle and Mario Fritz and Bernt Schiele},
url = {https://arxiv.org/abs/2009.09878
https://arxiv.org/pdf/2009.09878.pdf},
year = {2020},
date = {2020-12-06},
booktitle = {NeurIPS Workshop on Machine Learning for Autonomous Driving},
keywords = {2020},
pubstate = {published},
tppubtype = {workshop}
}

Close

  • https://arxiv.org/abs/2009.09878
  • https://arxiv.org/pdf/2009.09878.pdf

Close

Body Shape Privacy in Images: Understanding Privacy and Preventing Automatic Shape Extraction

Hosnieh Sattar; Katharina Krombholz; Gerard Pons-Moll; Mario Fritz

Body Shape Privacy in Images: Understanding Privacy and Preventing Automatic Shape Extraction Workshop

Workshop on The Bright and Dark Sides of Computer Vision: Challenges and Opportunities for Privacy and Security CVCOPS (ECCV-W), 2020.

Links | BibTeX | Tags: 2020

@workshop{cvcops20sattar,
title = {Body Shape Privacy in Images: Understanding Privacy and Preventing Automatic Shape Extraction},
author = {Hosnieh Sattar and Katharina Krombholz and Gerard Pons-Moll and Mario Fritz
},
url = {https://arxiv.org/abs/1905.11503
https://arxiv.org/pdf/1905.11503.pdf},
year = {2020},
date = {2020-08-28},
booktitle = {Workshop on The Bright and Dark Sides of Computer Vision: Challenges and Opportunities for Privacy and Security CVCOPS (ECCV-W)},
keywords = {2020},
pubstate = {published},
tppubtype = {workshop}
}

Close

  • https://arxiv.org/abs/1905.11503
  • https://arxiv.org/pdf/1905.11503.pdf

Close

Synthetic Convolutional Features for Improved Semantic Segmentation

Yang He; Bernt Schiele; Mario Fritz

Synthetic Convolutional Features for Improved Semantic Segmentation Workshop

Workshop on Assistive Computer Vision and Robotics at European Conference on Computer Vision (ECCV-W), 2020.

Links | BibTeX | Tags: 2020

@workshop{eccvw20he,
title = {Synthetic Convolutional Features for Improved Semantic Segmentation},
author = {Yang He and Bernt Schiele and Mario Fritz},
url = {https://arxiv.org/abs/2009.08849
https://arxiv.org/pdf/2009.08849.pdf},
year = {2020},
date = {2020-08-28},
booktitle = {Workshop on Assistive Computer Vision and Robotics at European Conference on Computer Vision (ECCV-W)},
keywords = {2020},
pubstate = {published},
tppubtype = {workshop}
}

Close

  • https://arxiv.org/abs/2009.08849
  • https://arxiv.org/pdf/2009.08849.pdf

Close

2019

Technical Reports

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

Yang He; Shadi Rahimian; Bernt Schiele; Mario Fritz

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

arXiv:1912.09685, 2019.

Links | BibTeX | Tags: 2019, 2020

@techreport{he19arxiv,
title = {Segmentations-Leak: Membership Inference Attacks and Defenses in Semantic Image Segmentation},
author = {Yang He and Shadi Rahimian and Bernt Schiele and Mario Fritz},
url = {https://arxiv.org/abs/1912.09685
https://arxiv.org/pdf/1912.09685.pdf},
year = {2019},
date = {2019-12-19},
type = {arXiv:1912.09685},
keywords = {2019, 2020},
pubstate = {published},
tppubtype = {techreport}
}

Close

  • https://arxiv.org/abs/1912.09685
  • https://arxiv.org/pdf/1912.09685.pdf

Close

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

Vedika Agarwal; Rakshith Shetty; Mario Fritz

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

2019.

Links | BibTeX | Tags: 2019, 2020

@techreport{agarwal19arxiv,
title = {Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editing},
author = {Vedika Agarwal and Rakshith Shetty and Mario Fritz
},
url = {https://arxiv.org/abs/1912.07538
https://arxiv.org/pdf/1912.07538.pdf},
year = {2019},
date = {2019-12-16},
keywords = {2019, 2020},
pubstate = {published},
tppubtype = {techreport}
}

Close

  • https://arxiv.org/abs/1912.07538
  • https://arxiv.org/pdf/1912.07538.pdf

Close


Imprint | Data Protection

    WordPress Theme Custom Community 2 developed by Macho Themes

    Back to Top