PPaperPicks

Mario Fritz

CISPA Helmholtz Center for Information Security, Saarland Informatics Campus, Germany

33 papers at tracked venues · 23 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0001-8949-9896 ↗Google Scholar ↗Homepage ↗

Venues

ICML ×5NeurIPS ×5ACL ×4CCS ×3EMNLP ×3ICLR ×3NAACL ×3AAAI ×1EACL ×1ECAI ×1MICCAI ×1S&P ×1USENIX Security ×1WACV ×1

Frequent coauthors

Ivaxi Sheth
×5
Hui-Po Wang
×5
Sahar Abdelnabi
×5
Zhixiong Zhuang
×4
Maria-Irina Nicolae
×4
Sarath Sivaprasad
×3
Yuxuan Zhou
×3
Margret Keuper
×3
Tobias Lorenz
×3
Bernt Schiele
×3
Vyas Raina
×2
Ruta Binkyte
×2

Papers

  1. Deepfake Detection that Generalizes Across Benchmarks
    WACV 2026 ·
    Andrii Yermakov
    ,
    Jan Cech
    ,
    Jiri Matas
    , Mario Fritz
  2. Funny or Persuasive, but Not Both: Evaluating Fine-Grained Multi-Concept Control in LLMs
    EACL 2026 ·
    Arya Labroo
    ,
    Ivaxi Sheth
    ,
    Vyas Raina
    ,
    Amaani Ahmed
    , Mario Fritz
  3. Inspectable AI for Science: A Research Object Approach to Generative AI Governance
    S&P 2026 ·
    Ruta Binkyte
    ,
    Sharif Abuaddba
    ,
    Chamikara Mahawaga Arachchige
    ,
    Ming Ding
    ,
    Natasha Fernandes
    , Mario Fritz
  4. Justice in Judgment: Unveiling (Hidden) Bias in LLM-assisted Peer Reviews
    ACL 2026 ·
    Sai Suresh Macharla Vasu
    ,
    Ivaxi Sheth
    ,
    Hui-Po Wang
    ,
    Ruta Binkyte
    , Mario Fritz
  5. ProxyPrompt: Securing System Prompts against Prompt Extraction Attacks
    ACL 2026 ·
    Zhixiong Zhuang
    ,
    Maria-Irina Nicolae
    ,
    Hui-Po Wang
    , Mario Fritz
  6. 3D-Sec '25: The 1st ACM Workshop on Deepfake, Deception, and Disinformation Security
    CCS 2025 ·
    Simon S. Woo
    ,
    Shahroz Tariq
    ,
    Sharif Abuadbba
    ,
    Kristen Moore
    ,
    Tim Walita
    ,
    Bimal Viswanath
    , Mario Fritz
  7. A Theory of Response Sampling in LLMs: Part Descriptive and Part Prescriptive
    ACL 2025 ·
    Sarath Sivaprasad
    ,
    Pramod Kaushik
    ,
    Sahar Abdelnabi
    , Mario Fritz
  8. Accept or Deny? Evaluating LLM Fairness and Performance in Loan Approval across Table-to-Text Serialization Approaches
    EMNLP 2025 ·
    Israel Abebe Azime
    ,
    Deborah Dormah Kanubala
    ,
    Tejumade Afonja
    , Mario Fritz,
    Isabel Valera
    ,
    Dietrich Klakow
    ,
    Philipp Slusallek
  9. Automated Detection of Abnormalities in Zebrafish Development
    MICCAI 2025 ·
    Sarath Sivaprasad
    ,
    Hui-Po Wang
    ,
    Anna-Lisa Jäckel
    ,
    Jonas Baumann
    ,
    Carole Baumann
    ,
    Jennifer Herrmann
    , Mario Fritz
  10. Balancing Diversity and Risk in LLM Sampling: How to Select Your Method and Parameter for Open-Ended Text Generation
    ACL 2025 ·
    Yuxuan Zhou
    ,
    Margret Keuper
    , Mario Fritz
  11. CSCS '25 - Cyber Security in CarS Workshop
    CCS 2025 ·
    Hans-Joachim Hof
    , Mario Fritz,
    Christoph Krauß
  12. Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?
    ICLR 2025 ·
    Egor Zverev
    ,
    Sahar Abdelnabi
    ,
    Soroush Tabesh
    , Mario Fritz,
    Christoph H. Lampert
  13. CausalGraph2LLM: Evaluating LLMs for Causal Queries
    NAACL 2025 ·
    Ivaxi Sheth
    ,
    Bahare Fatemi
    , Mario Fritz
  14. Context-Aware Reasoning On Parametric Knowledge for Inferring Causal Variables
    EMNLP 2025 ·
    Ivaxi Sheth
    ,
    Sahar Abdelnabi
    , Mario Fritz
  15. DocMIA: Document-Level Membership Inference Attacks against DocVQA Models
    ICLR 2025 ·
    Khanh Nguyen
    ,
    Raouf Kerkouche
    , Mario Fritz,
    Dimosthenis Karatzas
  16. MIBP-Cert: Certified Training against Data Perturbations with Mixed-Integer Bilinear Programs
    NeurIPS 2025 ·
    Tobias Lorenz
    ,
    Marta Kwiatkowska
    , Mario Fritz
  17. MaxSup: Overcoming Representation Collapse in Label Smoothing
    NeurIPS 2025 ·
    Yuxuan Zhou
    ,
    Heng Li
    ,
    Zhi-Qi Cheng
    ,
    Xudong Yan
    ,
    Yifei Dong
    , Mario Fritz,
    Margret Keuper
  18. Medical Multimodal Model Stealing Attacks via Adversarial Domain Alignment
    AAAI 2025 ·
    Yaling Shen
    ,
    Zhixiong Zhuang
    ,
    Kun Yuan
    ,
    Maria-Irina Nicolae
    ,
    Nassir Navab
    ,
    Nicolas Padoy
    , Mario Fritz
  19. Pixel-level Certified Explanations via Randomized Smoothing
    ICML 2025 ·
    Alaa Anani
    ,
    Tobias Lorenz
    , Mario Fritz,
    Bernt Schiele
  20. Stealix: Model Stealing via Prompt Evolution
    ICML 2025 ·
    Zhixiong Zhuang
    ,
    Hui-Po Wang
    ,
    Maria-Irina Nicolae
    , Mario Fritz
  21. Adaptive Hierarchical Certification for Segmentation using Randomized Smoothing
    ICML 2024 ·
    Alaa Anani
    ,
    Tobias Lorenz
    ,
    Bernt Schiele
    , Mario Fritz
  22. CSCS '24 - Cyber Security in CarS Workshop
    CCS 2024 · Mario Fritz,
    Christoph Krauß
    ,
    Hans-Joachim Hof
  23. Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation
    NeurIPS 2024 ·
    Sahar Abdelnabi
    ,
    Amr Gomaa
    ,
    Sarath Sivaprasad
    ,
    Lea Schönherr
    , Mario Fritz
  24. Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition
    NeurIPS 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
  25. Inside the Black Box: Detecting Data Leakage in Pre-Trained Language Encoders
    ECAI 2024 ·
    Yuan Xin
    ,
    Zheng Li
    ,
    Ning Yu
    ,
    Dingfan Chen
    , Mario Fritz,
    Michael Backes
    ,
    Yang Zhang
  26. LLM Task Interference: An Initial Study on the Impact of Task-Switch in Conversational History
    EMNLP 2024 ·
    Akash Gupta
    ,
    Ivaxi Sheth
    ,
    Vyas Raina
    ,
    Mark J. F. Gales
    , Mario Fritz
  27. Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior Models
    NeurIPS 2024 ·
    Hui-Po Wang
    , Mario Fritz
  28. MultiMax: Sparse and Multi-Modal Attention Learning
    ICML 2024 ·
    Yuxuan Zhou
    , Mario Fritz,
    Margret Keuper
  29. On Adversarial Training without Perturbing all Examples
    ICLR 2024 ·
    Max Maria Losch
    ,
    Mohamed Omran
    ,
    David Stutz
    , Mario Fritz,
    Bernt Schiele
  30. PoLLMgraph: Unraveling Hallucinations in Large Language Models via State Transition Dynamics
    NAACL 2024 ·
    Derui Zhu
    ,
    Dingfan Chen
    ,
    Qing Li
    ,
    Zongxiong Chen
    ,
    Lei Ma
    ,
    Jens Grossklags
    , Mario Fritz
  31. SecurityNet: Assessing Machine Learning Vulnerabilities on Public Models
    USENIX Security 2024 ·
    Boyang Zhang
    ,
    Zheng Li
    ,
    Ziqing Yang
    ,
    Xinlei He
    ,
    Michael Backes
    , Mario Fritz,
    Yang Zhang
  32. SimSCOOD: Systematic Analysis of Out-of-Distribution Generalization in Fine-tuned Source Code Models
    NAACL 2024 ·
    Hossein Hajipour
    ,
    Ning Yu
    ,
    Cristian-Alexandru Staicu
    , Mario Fritz
  33. Stealthy Imitation: Reward-guided Environment-free Policy Stealing
    ICML 2024 ·
    Zhixiong Zhuang
    ,
    Maria-Irina Nicolae
    , Mario Fritz