Our group is working on Trustworthy AI and AI Security and Safety in various domains like Cybersecurity, Health, Computer Vision, Natural Language Processing.
We are looking for PhD students and Post-Docs!
Please get in touch.
We also offer
student projects, bachelor/master thesis, internships.
Recent projects and initiatives related to trustworthy AI/ML, health, privacy:
Recent activities w.r.t. policy, regulation, outreach
- Frontier AI expert Findings on EU competitiveness, sovereignty and security
- Member of the AI Act Scientific Panel
- Expert for AI Cybersecurity Uplift Study “Toward Quantitative Modeling of Cybersecurity Risks Due to AI Misuse”
- Independent Expert study on technical means for implementing article 50 of EU AI Act towards the code of practice
- Scientific Lead of the CISPA-ELLIS Summerschool 2025 on “Trustworthy AI – Secure and Safe Foundation Models”
- Panel on “Loss of Control” at EU AI Office Workshop on “Towards defining best practices for systemic risk evaluations”
- Keynote on “Security and Safety of LLMs and AI Agents” at 18th ACM International Conference on Web Search and Data Mining
- Talk on “Fundamental Risks in the Current Deployment of General-Purpose AI Models: What Have We (Not) Learnt From Cybersecurity?” at European AI Office workshop “Evaluating General-Purpose AI Models with Systemic Risk”
- Expert opinion for evidence review report “Successful and timely uptake of artificial intelligence in science in the EU”
- Co-Author “ELSA Strategic Research Agenda: Facing the Grand Challenges of Secure and Safe AI”
- Co-Author “AI, Data, and Robotics ‘made in Europe’: Research agendas from the EU AI and robotics Networks of Excellence”
- Lecture at Artificial Intelligence Doctoral Academy (AIDA) on “Trustworthy AI and A Cybersecurity Perspective on Large Language Models”
2021
Journal Articles
Max Losch; Mario Fritz; Bernt Schiele
Semantic Bottlenecks: Quantifying and Improving Inspectability of Deep Representations Journal Article
In: International Journal of Computer Vision (IJCV), 2021.
@article{losch21ijcv,
title = {Semantic Bottlenecks: Quantifying and Improving Inspectability of Deep Representations},
author = {Max Losch and Mario Fritz and Bernt Schiele},
url = {https://link.springer.com/content/pdf/10.1007/s11263-021-01498-0.pdf},
year = {2021},
date = {2021-09-14},
journal = {International Journal of Computer Vision (IJCV)},
keywords = {2021},
pubstate = {published},
tppubtype = {article}
}
Marie Oestreich; Dingfan Chen; Joachim L. Schultze; Mario Fritz; Matthias Becker
Privacy considerations for sharing genomics data Journal Article
In: EXCLI Journal, 2021.
@article{oestreich21excli,
title = {Privacy considerations for sharing genomics data},
author = {Marie Oestreich and Dingfan Chen and Joachim L. Schultze and Mario Fritz and Matthias Becker},
url = {https://www.excli.de/index.php/excli/article/view/4002
https://www.excli.de/index.php/excli/article/view/4002/3892},
year = {2021},
date = {2021-07-16},
journal = {EXCLI Journal},
keywords = {2021},
pubstate = {published},
tppubtype = {article}
}
Proceedings Articles
Ning Yu; Vladislav Skripniuk; Sahar Abdelnabi; Mario Fritz
Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data Proceedings Article
In: International Conference on Computer Vision (ICCV), 2021.
@inproceedings{ning21iccv1,
title = {Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data},
author = {Ning Yu and Vladislav Skripniuk and Sahar Abdelnabi and Mario Fritz},
url = {preliminary version:
https://arxiv.org/abs/2007.08457
https://arxiv.org/pdf/2007.08457.pdf},
year = {2021},
date = {2021-10-12},
booktitle = {International Conference on Computer Vision (ICCV)},
keywords = {2021},
pubstate = {published},
tppubtype = {inproceedings}
}
Ning Yu; Guilin Liu; Aysegul Dundar; Andrew Tao; Bryan Catanzaro; Larry Davis; Mario Fritz
Dual Contrastive Loss and Attention for GANs Proceedings Article
In: International Conference on Computer Vision (ICCV), 2021.
@inproceedings{ning21iccv2,
title = {Dual Contrastive Loss and Attention for GANs},
author = {Ning Yu and Guilin Liu and Aysegul Dundar and Andrew Tao and Bryan Catanzaro and Larry Davis and Mario Fritz },
url = {preliminary version:
https://arxiv.org/abs/2103.16748
https://arxiv.org/pdf/2103.16748.pdf},
year = {2021},
date = {2021-10-11},
booktitle = {International Conference on Computer Vision (ICCV)},
keywords = {2021},
pubstate = {published},
tppubtype = {inproceedings}
}
Yang He; Ning Yu; Margret Keuper; Mario Fritz
Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis Proceedings Article
In: 30th International Joint Conference on Artificial Intelligence (IJCAI), 2021.
@inproceedings{he21ijcai,
title = {Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis},
author = {Yang He and Ning Yu and Margret Keuper and Mario Fritz},
url = {https://cispa.saarland/group/fritz/wp-content/blogs.dir/13/files/2021/05/ijcai21.pdf},
year = {2021},
date = {2021-08-21},
booktitle = {30th International Joint Conference on Artificial Intelligence (IJCAI)},
keywords = {2021},
pubstate = {published},
tppubtype = {inproceedings}
}
Moritz Bohle, Mario Fritz, Bernt Schiele
Convolutional Dynamic Alignment Networks for Interpretable Classifications Proceedings Article
In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
@inproceedings{moritz21cvpr,
title = {Convolutional Dynamic Alignment Networks for Interpretable Classifications},
author = {Moritz Bohle, Mario Fritz, Bernt Schiele},
url = {https://openaccess.thecvf.com/content/CVPR2021/papers/Bohle_Convolutional_Dynamic_Alignment_Networks_for_Interpretable_Classifications_CVPR_2021_paper.pdf},
year = {2021},
date = {2021-06-22},
booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
keywords = {2021},
pubstate = {published},
tppubtype = {inproceedings}
}
Apratim Bhattacharyya; Daniel Olmeda Reino; Mario Fritz; Bernt Schiele
Euro-PVI: Pedestrian Vehicle Interactions in Dense Urban Centers Proceedings Article
In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
@inproceedings{apratim21cvpr,
title = {Euro-PVI: Pedestrian Vehicle Interactions in Dense Urban Centers},
author = {Apratim Bhattacharyya and Daniel Olmeda Reino and Mario Fritz and Bernt Schiele},
url = {https://openaccess.thecvf.com/content/CVPR2021/papers/Bhattacharyya_Euro-PVI_Pedestrian_Vehicle_Interactions_in_Dense_Urban_Centers_CVPR_2021_paper.pdf
https://www.mpi-inf.mpg.de/departments/computer-vision-and-machine-learning/research/euro-pvi-dataset},
year = {2021},
date = {2021-06-21},
urldate = {2021-06-21},
booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
keywords = {2021},
pubstate = {published},
tppubtype = {inproceedings}
}
Hui-Po Wang; Ning Yu; Mario Fritz
Hijack-GAN: Unintended-Use of Pretrained, Black-Box GANs Proceedings Article
In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
@inproceedings{wang21cvpr,
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 = {2021},
date = {2021-06-19},
booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
keywords = {2021},
pubstate = {published},
tppubtype = {inproceedings}
}
Sahar Abdelnabi; Mario Fritz
Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hiding Proceedings Article
In: IEEE Symposium on Security and Privacy (S&P), 2021.
@inproceedings{abdelnabi21oakland,
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
https://github.com/S-Abdelnabi/awt
short video: https://www.youtube.com/watch?v=_Wc2OLVfD7Q
long video: https://www.youtube.com/watch?v=3wvgds9bYg4},
year = {2021},
date = {2021-05-21},
booktitle = {IEEE Symposium on Security and Privacy (S&P)},
keywords = {2021},
pubstate = {published},
tppubtype = {inproceedings}
}
Qiuhong Ke; Mario Fritz; Bernt Schiele
Future Moment Assessment for Action Query Proceedings Article
In: IEEE Winter Conference on Applications of Computer Vision (WACV ’20), 2021.
@inproceedings{wacv21ke,
title = {Future Moment Assessment for Action Query},
author = {Qiuhong Ke and Mario Fritz and Bernt Schiele},
url = {https://openaccess.thecvf.com/content/WACV2021/html/Ke_Future_Moment_Assessment_for_Action_Query_WACV_2021_paper.html
https://openaccess.thecvf.com/content/WACV2021/papers/Ke_Future_Moment_Assessment_for_Action_Query_WACV_2021_paper.pdf},
year = {2021},
date = {2021-01-05},
booktitle = {IEEE Winter Conference on Applications of Computer Vision (WACV ’20)},
keywords = {2021},
pubstate = {published},
tppubtype = {inproceedings}
}
Technical Reports
Tobias Lorenz; Marta Kwiatkowska; Mario Fritz
Backdoor Attacks on Network Certification via Data Poisoning Technical Report
arXiv:2108.11299, 2021.
@techreport{lorenz21arxiv,
title = {Backdoor Attacks on Network Certification via Data Poisoning},
author = {Tobias Lorenz and Marta Kwiatkowska and Mario Fritz},
url = {https://arxiv.org/abs/2108.11299
https://arxiv.org/pdf/2108.11299.pdf},
year = {2021},
date = {2021-08-25},
type = {arXiv:2108.11299},
keywords = {2021},
pubstate = {published},
tppubtype = {techreport}
}
Yugeng Liu; Rui Wen; Xinlei He; Ahmed Salem; Zhikun Zhang; Michael Backes; Emiliano De Cristofaro; Mario Fritz; Yang Zhang
ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models Technical Report
arXiv:2102.02551, 2021.
@techreport{liu21arxiv,
title = {ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models},
author = {Yugeng Liu and Rui Wen and Xinlei He and Ahmed Salem and Zhikun Zhang and Michael Backes and Emiliano De Cristofaro and Mario Fritz and Yang Zhang},
url = {https://arxiv.org/abs/2102.02551
https://arxiv.org/pdf/2102.02551.pdf},
year = {2021},
date = {2021-02-09},
type = {arXiv:2102.02551},
keywords = {2021},
pubstate = {published},
tppubtype = {techreport}
}
Workshops
Sahar Abdelnabi; Mario Fritz
"What's in the box?!": Deflecting Adversarial Attacks by Randomly Deploying Adversarially-Disjoint Models Workshop
Moving Target Defense Workshop in conjuncture with CCS, 2021.
@workshop{abdelnabi21ccsw,
title = {"What's in the box?!": Deflecting Adversarial Attacks by Randomly Deploying Adversarially-Disjoint Models},
author = {Sahar Abdelnabi and Mario Fritz},
url = {https://arxiv.org/abs/2102.05104
https://arxiv.org/pdf/2102.05104.pdf},
year = {2021},
date = {2021-11-15},
booktitle = {Moving Target Defense Workshop in conjuncture with CCS},
keywords = {2021},
pubstate = {published},
tppubtype = {workshop}
}
Hossein Hajipour; Apratim Bhattacharyya; Cristian-Alexandru Staicu; Mario Fritz
SampleFix: Learning to Generate Functionally Diverse Fixes Workshop
1st International Workshop on Machine Learning in Software Engineering in conjuncture with ECML PKDD, Springer, 2021.
@workshop{hajipour20pkddw,
title = {SampleFix: Learning to Generate Functionally Diverse Fixes},
author = {Hossein Hajipour and Apratim Bhattacharyya and Cristian-Alexandru Staicu and Mario Fritz},
url = {https://arxiv.org/abs/1906.10502
https://arxiv.org/pdf/1906.10502.pdf},
year = {2021},
date = {2021-09-17},
booktitle = {1st International Workshop on Machine Learning in Software Engineering in conjuncture with ECML PKDD},
publisher = {Springer},
keywords = {2021},
pubstate = {published},
tppubtype = {workshop}
}
Hossein Hajipour; Mateusz Malinowski; Mario Fritz
IReEn: Iterative Reverse-Engineering of Black-Box Functions via Neural Program Synthesis Workshop
1st International Workshop on Machine Learning in Software Engineering in conjuncture with ECML PKDD, Springer, 2021.
@workshop{hajipour21pkddw,
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 = {2021},
date = {2021-09-17},
booktitle = {1st International Workshop on Machine Learning in Software Engineering in conjuncture with ECML PKDD},
publisher = {Springer},
keywords = {2021},
pubstate = {published},
tppubtype = {workshop}
}
Hui-Po Wang; Tribhuvanesh Orekondy; Mario Fritz
InfoScrub: Towards Attribute Privacy by Targeted Obfuscation Workshop
CVPR Workshop on Fair, Data-Efficient, and Trusted Computer Vision (TCV), 2021.
@workshop{wang21cvprs,
title = {InfoScrub: Towards Attribute Privacy by Targeted Obfuscation},
author = {Hui-Po Wang and Tribhuvanesh Orekondy and Mario Fritz},
url = {https://arxiv.org/abs/2005.10329
https://arxiv.org/pdf/2005.10329.pdf},
year = {2021},
date = {2021-06-21},
booktitle = {CVPR Workshop on Fair, Data-Efficient, and Trusted Computer Vision (TCV)},
keywords = {2021},
pubstate = {published},
tppubtype = {workshop}
}
Lucjan Hanzlik; Yang Zhang; Kathrin Grosse; Ahmed Salem; Max Augustin; Michael Backes; Mario Fritz
MLCapsule: Guarded Offline Deployment of Machine Learning as a Service Workshop
CVPR Workshop on Fair, Data-Efficient, and Trusted Computer Vision (TCV), 2021.
@workshop{hanzlik21cvprw,
title = {MLCapsule: Guarded Offline Deployment of Machine Learning as a Service},
author = {Lucjan Hanzlik and Yang Zhang and Kathrin Grosse and Ahmed Salem and Max Augustin and Michael Backes and Mario Fritz},
url = {https://cispa.saarland/group/fritz/wp-content/blogs.dir/13/files/2021/06/mlcapsul_TCV_CR-4.pdf},
year = {2021},
date = {2021-06-20},
booktitle = {CVPR Workshop on Fair, Data-Efficient, and Trusted Computer Vision (TCV)},
keywords = {2021},
pubstate = {published},
tppubtype = {workshop}
}
