Mario Fritz

ORCID

Publication Activity (10 Years)

Years Active: 2002-2024
Publications (10 Years): 229

Top Venues

CoRR

CVPR

ICCV

USENIX Security Symposium

Darmstadt University of Technology, Germany (PHD)

Education History

Darmstadt University of Technology, Germany

PHD

Publications

Max Maria Losch, Mohamed Omran, David Stutz, Mario Fritz, Bernt Schiele
On Adversarial Training without Perturbing all Examples. ICLR (2024)
Derui Zhu, Dingfan Chen, Qing Li, Zongxiong Chen, Lei Ma, Jens Grossklags, Mario Fritz
PoLLMgraph: Unraveling Hallucinations in Large Language Models via State Transition Dynamics. CoRR (2024)
Hui-Po Wang, Dingfan Chen, Raouf Kerkouche, Mario Fritz
FedLAP-DP: Federated Learning by Sharing Differentially Private Loss Approximations. Proc. Priv. Enhancing Technol. 2024 (3) (2024)
Hossein Hajipour, Keno Hassler, Thorsten Holz, Lea Schönherr, Mario Fritz
CodeLMSec Benchmark: Systematically Evaluating and Finding Security Vulnerabilities in Black-Box Code Language Models. SaTML (2024)
Edoardo Debenedetti, Javier Rando, Daniel Paleka, Silaghi Fineas Florin, Dragos Albastroiu, Niv Cohen, Yuval Lemberg, Reshmi Ghosh, Rui Wen, Ahmed Salem, Giovanni Cherubin, Santiago Zanella Béguelin, Robin Schmid, Victor Klemm, Takahiro Miki, Chenhao Li, Stefan Kraft, Mario Fritz, Florian Tramèr, Sahar Abdelnabi, Lea Schönherr
Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition. CoRR (2024)
Zhixiong Zhuang, Maria-Irina Nicolae, Mario Fritz
Stealthy Imitation: Reward-guided Environment-free Policy Stealing. CoRR (2024)
Moritz Böhle, Navdeeppal Singh, Mario Fritz, Bernt Schiele
B-Cos Alignment for Inherently Interpretable CNNs and Vision Transformers. IEEE Trans. Pattern Anal. Mach. Intell. 46 (6) (2024)
Sahar Abdelnabi, Aideen Fay, Giovanni Cherubin, Ahmed Salem, Mario Fritz, Andrew Paverd
Are you still on track!? Catching LLM Task Drift with Activations. CoRR (2024)
Egor Zverev, Sahar Abdelnabi, Mario Fritz, Christoph H. Lampert
Can LLMs Separate Instructions From Data? And What Do We Even Mean By That? CoRR (2024)
Boyang Zhang, Zheng Li, Ziqing Yang, Xinlei He, Michael Backes, Mario Fritz, Yang Zhang
SecurityNet: Assessing Machine Learning Vulnerabilities on Public Models. USENIX Security Symposium (2024)
Yuxuan Zhou, Mario Fritz, Margret Keuper
MultiMax: Sparse and Multi-Modal Attention Learning. CoRR (2024)
Alaa Anani, Tobias Lorenz, Bernt Schiele, Mario Fritz
Adaptive Hierarchical Certification for Segmentation using Randomized Smoothing. CoRR (2024)
Dingfan Chen, Raouf Kerkouche, Mario Fritz
A Unified View of Differentially Private Deep Generative Modeling. Trans. Mach. Learn. Res. 2024 (2024)
Sarath Sivaprasad, Pramod Kaushik, Sahar Abdelnabi, Mario Fritz
Exploring Value Biases: How LLMs Deviate Towards the Ideal. CoRR (2024)
Dingfan Chen, Marie Oestreich, Tejumade Afonja, Raouf Kerkouche, Matthias Becker, Mario Fritz
Towards Biologically Plausible and Private Gene Expression Data Generation. CoRR (2024)
Akash Gupta, Ivaxi Sheth, Vyas Raina, Mark J. F. Gales, Mario Fritz
LLM Task Interference: An Initial Study on the Impact of Task-Switch in Conversational History. CoRR (2024)
Tobias Lorenz, Marta Kwiatkowska, Mario Fritz
FullCert: Deterministic End-to-End Certification for Training and Inference of Neural Networks. CoRR (2024)
Sahar Abdelnabi, Amr Gomaa, Sarath Sivaprasad, Lea Schönherr, Mario Fritz
LLM-Deliberation: Evaluating LLMs with Interactive Multi-Agent Negotiation Games. CoRR (2023)
Moritz Böhle, Navdeeppal Singh, Mario Fritz, Bernt Schiele
B-cos Alignment for Inherently Interpretable CNNs and Vision Transformers. CoRR (2023)
Shadi Rahimian, Raouf Kerkouche, Ina Kurth, Mario Fritz
Private and Collaborative Kaplan-Meier Estimators. CoRR (2023)
Dingfan Chen, Raouf Kerkouche, Mario Fritz
A Unified View of Differentially Private Deep Generative Modeling. CoRR (2023)
Derui Zhu, Dingfan Chen, Jens Grossklags, Mario Fritz
Data Forensics in Diffusion Models: A Systematic Analysis of Membership Privacy. CoRR (2023)
Max Maria Losch, David Stutz, Bernt Schiele, Mario Fritz
Certified Robust Models with Slack Control and Large Lipschitz Constants. CoRR (2023)
Boyang Zhang, Zheng Li, Ziqing Yang, Xinlei He, Michael Backes, Mario Fritz, Yang Zhang
SecurityNet: Assessing Machine Learning Vulnerabilities on Public Models. CoRR (2023)
Rubèn Tito, Khanh Nguyen, Marlon Tobaben, Raouf Kerkouche, Mohamed Ali Souibgui, Kangsoo Jung, Lei Kang, Ernest Valveny, Antti Honkela, Mario Fritz, Dimosthenis Karatzas
Privacy-Aware Document Visual Question Answering. CoRR (2023)
Sarath Sivaprasad, Mario Fritz
Going Beyond Familiar Features for Deep Anomaly Detection. CoRR (2023)
Zheng Li, Ning Yu, Ahmed Salem, Michael Backes, Mario Fritz, Yang Zhang
UnGANable: Defending Against GAN-based Face Manipulation. USENIX Security Symposium (2023)
Raouf Kerkouche, Gergely Ács, Mario Fritz
Client-specific Property Inference against Secure Aggregation in Federated Learning. WPES@CCS (2023)
Tobias Lorenz, Marta Kwiatkowska, Mario Fritz
Certifiers Make Neural Networks Vulnerable to Availability Attacks. AISec@CCS (2023)
Moritz Böhle, Mario Fritz, Bernt Schiele
Optimising for Interpretability: Convolutional Dynamic Alignment Networks. IEEE Trans. Pattern Anal. Mach. Intell. 45 (6) (2023)
Moritz Böhle, Mario Fritz, Bernt Schiele
Holistically Explainable Vision Transformers. CoRR (2023)
Giada Stivala, Sahar Abdelnabi, Andrea Mengascini, Mariano Graziano, Mario Fritz, Giancarlo Pellegrino
From Attachments to SEO: Click Here to Learn More about Clickbait PDFs! ACSAC (2023)
Kai Greshake, Sahar Abdelnabi, Shailesh Mishra, Christoph Endres, Thorsten Holz, Mario Fritz
More than you've asked for: A Comprehensive Analysis of Novel Prompt Injection Threats to Application-Integrated Large Language Models. CoRR (2023)
Protik Bose Pranto, Waqar Hassan Khan, Sahar Abdelnabi, Rebecca Weil, Mario Fritz, Rakibul Hasan
From Bad to Worse: Using Private Data to Propagate Disinformation on Online Platforms with a Greater Efficiency. CoRR (2023)
Raouf Kerkouche, Gergely Ács, Mario Fritz
Client-specific Property Inference against Secure Aggregation in Federated Learning. CoRR (2023)
Sahar Abdelnabi, Kai Greshake, Shailesh Mishra, Christoph Endres, Thorsten Holz, Mario Fritz
Not What You've Signed Up For: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection. AISec@CCS (2023)
Giada Stivala, Sahar Abdelnabi, Andrea Mengascini, Mariano Graziano, Mario Fritz, Giancarlo Pellegrino
A Large-Scale Study of Phishing PDF Documents. CoRR (2023)
Tejumade Afonja, Dingfan Chen, Mario Fritz
MargCTGAN: A "Marginally" Better CTGAN for the Low Sample Regime. CoRR (2023)
Tejumade Afonja, Dingfan Chen, Mario Fritz
MargCTGAN: A "Marginally" Better CTGAN for the Low Sample Regime. DAGM (2023)
Max Maria Losch, David Stutz, Bernt Schiele, Mario Fritz
Certified Robust Models with Slack Control and Large Lipschitz Constants. DAGM (2023)
Sahar Abdelnabi, Mario Fritz
Fact-Saboteurs: A Taxonomy of Evidence Manipulation Attacks against Fact-Verification Systems. USENIX Security Symposium (2023)
Hossein Hajipour, Thorsten Holz, Lea Schönherr, Mario Fritz
Systematically Finding Security Vulnerabilities in Black-Box Code Generation Models. CoRR (2023)
Hui-Po Wang, Dingfan Chen, Raouf Kerkouche, Mario Fritz
Fed-GLOSS-DP: Federated, Global Learning using Synthetic Sets with Record Level Differential Privacy. CoRR (2023)
Shadi Rahimian, Raouf Kerkouche, Ina Kurth, Mario Fritz
Practical Challenges in Differentially-Private Federated Survival Analysis of Medical Data. CHIL (2022)
Sahar Abdelnabi, Mario Fritz
Fact-Saboteurs: A Taxonomy of Evidence Manipulation Attacks against Fact-Verification Systems. CoRR (2022)
Hui-Po Wang, Sebastian U. Stich, Yang He, Mario Fritz
ProgFed: Effective, Communication, and Computation Efficient Federated Learning by Progressive Training. ICML (2022)
Shadi Rahimian, Raouf Kerkouche, Ina Kurth, Mario Fritz
Practical Challenges in Differentially-Private Federated Survival Analysis of Medical Data. CoRR (2022)
Sahar Abdelnabi, Rakibul Hasan, Mario Fritz
Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resources. CVPR (2022)
Hossein Hajipour, Ning Yu, Cristian-Alexandru Staicu, Mario Fritz
SimSCOOD: Systematic Analysis of Out-of-Distribution Behavior of Source Code Models. CoRR (2022)
Dingfan Chen, Ning Yu, Mario Fritz
RelaxLoss: Defending Membership Inference Attacks without Losing Utility. CoRR (2022)
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. USENIX Security Symposium (2022)
Rakibul Hasan, Mario Fritz
Understanding Utility and Privacy of Demographic Data in Education Technology by Causal Analysis and Adversarial-Censoring. Proc. Priv. Enhancing Technol. 2022 (2) (2022)
Dingfan Chen, Ning Yu, Mario Fritz
RelaxLoss: Defending Membership Inference Attacks without Losing Utility. ICLR (2022)
Dingfan Chen, Raouf Kerkouche, Mario Fritz
Private Set Generation with Discriminative Information. NeurIPS (2022)
Moritz Böhle, Mario Fritz, Bernt Schiele
B-cos Networks: Alignment is All We Need for Interpretability. CVPR (2022)
Dingfan Chen, Raouf Kerkouche, Mario Fritz
Private Set Generation with Discriminative Information. CoRR (2022)
Moritz Böhle, Mario Fritz, Bernt Schiele
B-cos Networks: Alignment is All We Need for Interpretability. CoRR (2022)
Ning Yu, Vladislav Skripniuk, Dingfan Chen, Larry S. Davis, Mario Fritz
Responsible Disclosure of Generative Models Using Scalable Fingerprinting. ICLR (2022)
Zheng Li, Ning Yu, Ahmed Salem, Michael Backes, Mario Fritz, Yang Zhang
UnGANable: Defending Against GAN-based Face Manipulation. CoRR (2022)
Hossein Hajipour, Apratim Bhattacharyya, Cristian-Alexandru Staicu, Mario Fritz
SampleFix: Learning to Generate Functionally Diverse Fixes. PKDD/ECML Workshops (2) (2021)
Moritz Böhle, Mario Fritz, Bernt Schiele
Optimising for Interpretability: Convolutional Dynamic Alignment Networks. CoRR (2021)
Sahar Abdelnabi, Mario Fritz
"What's in the box?!": Deflecting Adversarial Attacks by Randomly Deploying Adversarially-Disjoint Models. CoRR (2021)
Hui-Po Wang, Tribhuvanesh Orekondy, Mario Fritz
InfoScrub: Towards Attribute Privacy by Targeted Obfuscation. CVPR Workshops (2021)
Lucjan Hanzlik, Yang Zhang, Kathrin Grosse, Ahmed Salem, Maximilian Augustin, Michael Backes, Mario Fritz
MLCapsule: Guarded Offline Deployment of Machine Learning as a Service. CVPR Workshops (2021)
Moritz Böhle, Mario Fritz, Bernt Schiele
Convolutional Dynamic Alignment Networks for Interpretable Classifications. CVPR (2021)
Yang He, Ning Yu, Margret Keuper, Mario Fritz
Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis. CoRR (2021)
Ning Yu, Vladislav Skripniuk, Sahar Abdelnabi, Mario Fritz
Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data. ICCV (2021)
Hui-Po Wang, Sebastian U. Stich, Yang He, Mario Fritz
ProgFed: Effective, Communication, and Computation Efficient Federated Learning by Progressive Training. CoRR (2021)
Ning Yu, Guilin Liu, Aysegul Dundar, Andrew Tao, Bryan Catanzaro, Larry Davis, Mario Fritz
Dual Contrastive Loss and Attention for GANs. CoRR (2021)
Ning Yu, Guilin Liu, Aysegul Dundar, Andrew Tao, Bryan Catanzaro, Larry Davis, Mario Fritz
Dual Contrastive Loss and Attention for GANs. ICCV (2021)
Hui-Po Wang, Ning Yu, Mario Fritz
Hijack-GAN: Unintended-Use of Pretrained, Black-Box GANs. CVPR (2021)
Apratim Bhattacharyya, Daniel Olmeda Reino, Mario Fritz, Bernt Schiele
Euro-PVI: Pedestrian Vehicle Interactions in Dense Urban Centers. CVPR (2021)
Max Maria Losch, Mario Fritz, Bernt Schiele
Semantic Bottlenecks: Quantifying and Improving Inspectability of Deep Representations. Int. J. Comput. Vis. 129 (11) (2021)
Sahar Abdelnabi, Mario Fritz
Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hiding. IEEE Symposium on Security and Privacy (2021)
Apratim Bhattacharyya, Daniel Olmeda Reino, Mario Fritz, Bernt Schiele
Euro-PVI: Pedestrian Vehicle Interactions in Dense Urban Centers. CoRR (2021)
Tobias Lorenz, Marta Kwiatkowska, Mario Fritz
Backdoor Attacks on Network Certification via Data Poisoning. CoRR (2021)
Shadi Rahimian, Tribhuvanesh Orekondy, Mario Fritz
Differential Privacy Defenses and Sampling Attacks for Membership Inference. AISec@CCS (2021)
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. CoRR (2021)
Sahar Abdelnabi, Mario Fritz
What's in the box: Deflecting Adversarial Attacks by Randomly Deploying Adversarially-Disjoint Models. MTD@CCS (2021)
Sahar Abdelnabi, Rakibul Hasan, Mario Fritz
Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resources. CoRR (2021)
Qiuhong Ke, Mario Fritz, Bernt Schiele
Future Moment Assessment for Action Query. WACV (2021)
Hossein Hajipour, Mateusz Malinowski, Mario Fritz
IReEn: Reverse-Engineering of Black-Box Functions via Iterative Neural Program Synthesis. PKDD/ECML Workshops (2) (2021)
Yang He, Ning Yu, Margret Keuper, Mario Fritz
Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis. IJCAI (2021)
Moritz Böhle, Mario Fritz, Bernt Schiele
Convolutional Dynamic Alignment Networks for Interpretable Classifications. CoRR (2021)
Hui-Po Wang, Tribhuvanesh Orekondy, Mario Fritz
InfoScrub: Towards Attribute Privacy by Targeted Obfuscation. CoRR (2020)
Hosnieh Sattar, Mario Fritz, Andreas Bulling
Deep gaze pooling: Inferring and visually decoding search intents from human gaze fixations. Neurocomputing 387 (2020)
Ning Yu, Ke Li, Peng Zhou, Jitendra Malik, Larry Davis, Mario Fritz
Inclusive GAN: Improving Data and Minority Coverage in Generative Models. ECCV (22) (2020)
Dingfan Chen, Ning Yu, Yang Zhang, Mario Fritz
GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models. CCS (2020)
Ning Yu, Ke Li, Peng Zhou, Jitendra Malik, Larry Davis, Mario Fritz
Inclusive GAN: Improving Data and Minority Coverage in Generative Models. CoRR (2020)
Thomas Brox, Mario Fritz
Editor's Note. Int. J. Comput. Vis. 128 (4) (2020)
Vedika Agarwal, Rakshith Shetty, Mario Fritz
Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editing. CVPR (2020)
Yang He, Bernt Schiele, Mario Fritz
Synthetic Convolutional Features for Improved Semantic Segmentation. CoRR (2020)
Apratim Bhattacharyya, Christoph-Nikolas Straehle, Mario Fritz, Bernt Schiele
Haar Wavelet based Block Autoregressive Flows for Trajectories. CoRR (2020)
Dingfan Chen, Tribhuvanesh Orekondy, Mario Fritz
GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators. CoRR (2020)
Max Maria Losch, Mario Fritz, Bernt Schiele
Semantic Bottlenecks: Quantifying and Improving Inspectability of Deep Representations. GCPR (2020)
Yang He, Bernt Schiele, Mario Fritz
Synthetic Convolutional Features for Improved Semantic Segmentation. ECCV Workshops (4) (2020)
Shadi Rahimian, Tribhuvanesh Orekondy, Mario Fritz
Sampling Attacks: Amplification of Membership Inference Attacks by Repeated Queries. CoRR (2020)
Rakibul Hasan, David J. Crandall, Mario Fritz, Apu Kapadia
Automatically Detecting Bystanders in Photos to Reduce Privacy Risks. IEEE Symposium on Security and Privacy (2020)
Ahmed Salem, Apratim Bhattacharya, Michael Backes, Mario Fritz, Yang Zhang
Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learning. USENIX Security Symposium (2020)
Tribhuvanesh Orekondy, Bernt Schiele, Mario Fritz
Prediction Poisoning: Towards Defenses Against DNN Model Stealing Attacks. ICLR (2020)

Mario Fritz.css-eqlu8i{font-size:small;padding-left:4px;}

Publication Activity (10 Years)

Top Topics

Top Venues

Mario Fritz