🧑‍🔬 Mario Fritz

🏛️ Affiliations

🔬Helmholtz Center for Information SecuritySaarbrücken · Germany2018–2026 · 172 paperscurrent🔬Max Planck Institute for InformaticsSaarbrücken · Germany2011–2022 · 112 papers🔬Max Planck SocietyMunich · Germany2011–2021 · 46 papers🎓University of California, BerkeleyBerkeley · United States2009–2011 · 13 papers🎓Technische Universität DarmstadtDarmstadt · Germany2005–2019 · 10 papersEducation🔬International Computer Science InstituteBerkeley · United States2009–2011 · 7 papers🎓Saarland UniversitySaarbrücken · Germany2014–2025 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 5 more institutions on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection (2023 · 239 citations)
   Earlier work on prompt injection assumed that the attacker is the user, typing malicious instructions straight into the model.
2. Balancing Diversity and Risk in LLM Sampling: How to Select Your Method and Parameter for Open-Ended Text Generation (2025 · 11 citations)
   Truncation sampling methods for LLM decoding are usually compared on open-ended generation benchmarks. Those comparisons are fragile for two reasons. First, outcomes depend heavily on hand-tuned parameters, which are typically swept over a coarse grid. Second, the reference texts are limited. The authors propose an…
3. Justice in Judgment: Unveiling (Hidden) Bias in LLM-assisted Peer Reviews (2026 · 8 citations)
   Peer review is increasingly assisted or even fully generated by LLMs. This paper asks whether such systems treat authors differently depending on who they are. The authors simulate a single-blind setting and build a counterfactual audit. Each paper is reviewed many times, and only one piece of author metadata changes…
4. ProxyPrompt: Securing System Prompts against Prompt Extraction Attacks (2026 · 1 citation)
   System prompts for LLM applications often represent significant engineering effort and may contain confidential rules, filtering criteria or business logic.

All works

35 works of theirs in our library, the most cited first; 4 with a page here, the others link their original until we summarise them.

1. Adapting Visual Category Models to New Domains ↗Lecture notes in computer science · no summary yetKate Saenko et al.2010 · 2,751 citations
2. The 2005 PASCAL Visual Object Classes Challenge ↗Lecture notes in computer science · no summary yetMark Everingham et al.2006 · 743 citations
3. Knockoff Nets: Stealing Functionality of Black-Box Models ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetTribhuvanesh Orekondy, Bernt Schiele, Mario Fritz2019 · 556 citations
4. Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetNing Yu, Larry Steven Davis, Mario Fritz2019 · 445 citations
5. A Category-Level 3D Object Dataset: Putting the Kinect to Work ↗Advances in computer vision and pattern recognition · no summary yetAllison Janoch et al.2012 · 258 citations
6. A category-level 3-D object dataset: Putting the Kinect to work ↗IEEE International Conference on Computer Vision Workshops · no summary yetAllison Janoch et al.2011 · 253 citations
7. A geometric approach to robotic laundry folding ↗The International Journal of Robotics Research · no summary yetStephen Miller et al.2011 · 242 citations
8. Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt InjectionarXiv:2302.12173Kai Greshake, Sahar Abdelnabi, Shailesh Mishra, et al.2023 · 239 citations
9. Machine Learning Challenges. Evaluating Predictive Uncertainty, Visual Object Classification, and Recognising Tectual Entailment ↗Lecture notes in computer science · no summary yetMark Everingham et al.2006 · 218 citations
10. Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetNing Yu et al.2021 · 197 citations
11. Exploiting Saliency for Object Segmentation from Image Level Labels ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetSeong Joon Oh et al.2017 · 193 citations
12. Time-Conditioned Action Anticipation in One Shot ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetQiuhong Ke, Mario Fritz, Bernt Schiele2019 · 110 citations
13. Multi-cue Zero-Shot Learning with Strong Supervision ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetZeynep Akata et al.2016 · 108 citations
14. Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resources ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetSahar Abdelnabi, Rakibul Hasan, Mario Fritz2022 · 106 citations
15. The NBNN kernel ↗International Conference on Computer Vision · no summary yetTinne Tuytelaars et al.2011 · 100 citations
16. Deep Reflectance Maps ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetKonstantinos Rematas et al.2016 · 98 citations
17. Parametrized shape models for clothing ↗Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · no summary yetStephen D. Miller et al.2011 · 93 citations
18. Multi-class Video Co-segmentation with a Generative Multi-video Model ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetWei-Chen Chiu, Mario Fritz2013 · 84 citations
19. Sparselet Models for Efficient Multiclass Object Detection ↗Lecture notes in computer science · no summary yetHyun Oh Song et al.2012 · 78 citations
20. B-cos Networks: Alignment is All We Need for Interpretability ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetMoritz Böhle, Mario Fritz, Bernt Schiele2022 · 71 citations
21. Learning to Detect Visual Grasp Affordance ↗IEEE Transactions on Automation Science and Engineering · no summary yetHyun Oh Song et al.2015 · 62 citations
22. An Additive Latent Feature Model for Transparent Object Recognition ↗Max Planck Digital Library · no summary yetMario Fritz et al.2009 · 59 citations
23. Dual Contrastive Loss and Attention for GANs ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetNing Yu et al.2021 · 53 citations
24. Anytime Recognition of Objects and Scenes ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetSergey Karayev, Mario Fritz, Trevor Jackson Darrell2014 · 48 citations
25. Timely Object Recognition ↗no summary yetSergey Karayev et al.2012 · 39 citations

See all 35 works by Mario Fritz →

🤝 Co-authors here

1 co-author with a page, the most papers together first.

• Hui-Po Wang ×2

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings ×9
• Lecture notes in computer science ×4
• IEEE/CVF International Conference on Computer Vision (ICCV) ×3
• Findings of the Association for Computational Linguistics ×2: Findings of the Association for Computational Linguistics 2026 ×2
• IEEE International Conference on Computer Vision Workshops ×2
• IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) ×2
• UC Berkeley ×2
• Annual Meeting of the Association for Computational Linguistics (ACL): ACL 2025
• Advances in computer vision and pattern recognition
• Elsevier eBooks
• IEEE Transactions on Automation Science and Engineering
• International Conference on Computer Vision

🔗 Cited by

Papers of our library cite their works 371 times (of the 149,439 papers whose bibliographies we read); 45 citing papers with a page here →.

Updated 1 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/mario-fritz/