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 health, privacy, AI:
- 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:
- ICLR’22: Responsible Disclosure of Generative Models Using Scalable Fingerprinting
- ArXiv’21: Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resources
- 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:
- 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
- NeurIPS’20: GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators
- NeurIPS-W’20: SampleFix: Learning to Correct Programs by Sampling Diverse Fixes
- NeurIPS-W’20: IReEn: Iterative Reverse-Engineering of Black-Box Functions via Neural Program Synthesis
- NeurIPS-W’20: Haar Wavelet based Block Autoregressive Flows for Trajectories
- CCS’20: VisualPhishNet: Zero-Day Phishing Website Detection by Visual Similarity
- CCS’20: GAN-Leaks: A Taxonomy of Membership Inference Attacks against GANs
- S&P’20: Automatically Detecting Bystanders in Photos to Reduce Privacy Risks
- USENIX Security’20: Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learning
- ICLR’20: Prediction Poisoning: Utility-Constrained Defenses Against Model Stealing Attacks
- CVPR’20: Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editing
- CVPR’20: Normalizing Flows with Multi-scale Autoregressive Priors
- ECCV’20: Towards Automated Testing and Robustification by Semantic Adversarial Data Generation
- ECCV’20: Inclusive GAN: Improving Data and Minority Coverage in Generative Models
- ECCV’20: Segmentations-Leak: Membership Inference Attacks and Defenses in Semantic Image Segmentation
- ECCV-W’20: Body Shape Privacy in Images: Understanding Privacy and Preventing Automatic Shape Extraction
- ECCV-W’20: Synthetic Convolutional Features for Improved Semantic Segmentation
- NEUCOM’20: Deep gaze pooling: Inferring and visually decoding search intents from human gaze fixations
- GCPR’20: Semantic Bottlenecks: Quantifying & Improving Inspectability of Deep Representations
- GCPR’20: Long-Tailed Recognition Using Class-Balanced Experts
- GCPR’20: Haar Wavelet based Block Autoregressive Flows for Trajectories
- TPAMI’20: Person Recognition in Personal Photo Collections
- Explainable AI Book: Towards reverse-engineering black-box neural networks
Most recent work on ArXiv:
- ArXiv’21: Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resources
- ArXiv’21: Backdoor Attacks on Network Certification via Data Poisoning
- ArXiv’21: Responsible Disclosure of Generative Models Using Scalable Fingerprinting
- ArXiv’20: CosSGD: Nonlinear Quantization for Communication-efficient Federated Learning
News, talks, events:
- 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)
2020
Inproceedings
Prediction Poisoning: Utility-Constrained Defenses Against Model Stealing Attacks Inproceedings
In: International Conference on Representation Learning (ICLR), 2020.
Technical Reports
InfoScrub: Towards Attribute Privacy by Targeted Obfuscation Technical Report
arXiv:2005.10329 , 2020.
Workshops
SampleFix: Learning to Correct Programs by Sampling Diverse Fixes Workshop
NeurIPS Workshop on Computer-Assisted Programming, 2020.
2019
Journal Articles
MPIIGaze: Real-World Dataset and Deep Appearance-Based Gaze Estimation Journal Article
In: Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2019.
Incollections
Towards reverse-engineering black-box neural networks Incollection
In: Explainable AI: Interpreting, Explaining and Visualizing Deep Learning, 2019.
Inproceedings
Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints Inproceedings
In: International Conference on Computer Vision (ICCV), 2019.
Deep Appearance Maps Inproceedings
In: International Conference on Computer Vision (ICCV), 2019.
Knockoff Nets: Stealing Functionality of Black-Box Models Inproceedings
In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
Not Using the Car to See the Sidewalk: Quantifying and Controlling the Effects of Context in Classification and Segmentation Inproceedings
In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
Time-Conditioned Action Anticipation in One Shot Inproceedings
In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
Bayesian Prediction of Future Street Scenes using Synthetic Likelihoods Inproceedings
In: International Conference on Representation Learning (ICLR), 2019.
ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models Inproceedings
In: Annual Network and Distributed System Security Symposium (NDSS), 2019, (to appear).
Fashion is Taking Shape: Understanding Clothing Preference Based on Body Shape From Online Sources Inproceedings
In: IEEE Winter Conference on Applications of Computer Vision (WACV), 2019, (to appear).
Technical Reports
Segmentations-Leak: Membership Inference Attacks and Defenses in Semantic Image Segmentation Technical Report
arXiv:1912.09685, 2019.
"Best-of-Many-Samples" Distribution Matching Technical Report
arXiv:1909.12598, 2019.
GAN-Leaks: A Taxonomy of Membership Inference Attacks against GANs Technical Report
arXiv:1909.03935, 2019.
WhiteNet: Phishing Website Detection by Visual Whitelists Technical Report
arXiv:1909.00300, 2019.
Conditional Flow Variational Autoencoders for Structured Sequence Prediction Technical Report
arXiv:1908.09008, 2019.
Interpretability Beyond Classification Output: Semantic Bottleneck Networks Technical Report
arXiv:1907.10882 , 2019.
Prediction Poisoning: Utility-Constrained Defenses Against Model Stealing Attacks Technical Report
2019.
SampleFix: Learning to Correct Programs by Sampling Diverse Fixes Technical Report
arXiv:1906.10502, 2019.
Shape Evasion: Preventing Body Shape Inference of Multi-Stage Approaches Technical Report
arXiv:1905.11503 , 2019.
Learning Manipulation under Physics Constraints with Visual Perception Technical Report
2019.
Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learning Technical Report
2019.
Workshops
Differential Privacy Defenses and Sampling Attacks for Membership Inference Workshop
NeurIPS Workshop on Privacy in Machine Learning (PRIML), 2019.
Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learning Workshop
Hot Topics in Privacy Enhancing Technologies (HotPETs), 2019.
Understanding and Recognizing Bystanders in Images for Privacy Protection Workshop
Privacy, Usability, and Transparency (PUT) @ PETs, 2019.