PPaperPicks

Mario Fritz

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

28 papers at tracked venues · 18 at CORE A* · active 2024–2026

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

Venues

ICML ×5NeurIPS ×5ACL ×4EMNLP ×3ICLR ×3NAACL ×3AAAI ×1EACL ×1ECAI ×1MICCAI ×1WACV ×1

Frequent coauthors

Zhixiong Zhuang
DBLP profile ↗ORCID search ↗
×3
Yuxuan Zhou
DBLP profile ↗ORCID search ↗
×3
Sarath Sivaprasad
DBLP profile ↗ORCID search ↗
×2
Ivaxi Sheth
DBLP profile ↗ORCID search ↗
×2
Alaa Anani
DBLP profile ↗ORCID search ↗
×2
Andrii Yermakov
DBLP profile ↗ORCID search ↗
×1
Arya Labroo
DBLP profile ↗ORCID search ↗
×1
Sai Suresh Macharla Vasu
DBLP profile ↗ORCID search ↗
×1
Israel Abebe Azime
DBLP profile ↗ORCID search ↗
×1
Egor Zverev
DBLP profile ↗ORCID search ↗
×1
Khanh Nguyen
DBLP profile ↗ORCID search ↗
×1
Tobias Lorenz
DBLP profile ↗ORCID search ↗
×1

Papers

  1. Deepfake Detection that Generalizes Across Benchmarks
    WACV 2026 ·
    Andrii Yermakov
    DBLP profile ↗ORCID search ↗
  2. Funny or Persuasive, but Not Both: Evaluating Fine-Grained Multi-Concept Control in LLMs
    EACL 2026 ·
    Arya Labroo
    DBLP profile ↗ORCID search ↗
  3. Justice in Judgment: Unveiling (Hidden) Bias in LLM-assisted Peer Reviews
    ACL 2026 ·
    Sai Suresh Macharla Vasu
    DBLP profile ↗ORCID search ↗
  4. ProxyPrompt: Securing System Prompts against Prompt Extraction Attacks
    ACL 2026 ·
    Zhixiong Zhuang
    DBLP profile ↗ORCID search ↗
  5. A Theory of Response Sampling in LLMs: Part Descriptive and Part Prescriptive
    ACL 2025 ·
    Sarath Sivaprasad
    DBLP profile ↗ORCID search ↗
  6. Accept or Deny? Evaluating LLM Fairness and Performance in Loan Approval across Table-to-Text Serialization Approaches
    EMNLP 2025 ·
    Israel Abebe Azime
    DBLP profile ↗ORCID search ↗
  7. Automated Detection of Abnormalities in Zebrafish Development
    MICCAI 2025 ·
    Sarath Sivaprasad
    DBLP profile ↗ORCID search ↗
  8. Balancing Diversity and Risk in LLM Sampling: How to Select Your Method and Parameter for Open-Ended Text Generation
    ACL 2025 ·
    Yuxuan Zhou
    DBLP profile ↗ORCID search ↗
  9. Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?
    ICLR 2025 ·
    Egor Zverev
    DBLP profile ↗ORCID search ↗
  10. CausalGraph2LLM: Evaluating LLMs for Causal Queries
    NAACL 2025 ·
    Ivaxi Sheth
    DBLP profile ↗ORCID search ↗
  11. Context-Aware Reasoning On Parametric Knowledge for Inferring Causal Variables
    EMNLP 2025 ·
    Ivaxi Sheth
    DBLP profile ↗ORCID search ↗
  12. DocMIA: Document-Level Membership Inference Attacks against DocVQA Models
    ICLR 2025 ·
    Khanh Nguyen
    DBLP profile ↗ORCID search ↗
  13. MIBP-Cert: Certified Training against Data Perturbations with Mixed-Integer Bilinear Programs
    NeurIPS 2025 ·
    Tobias Lorenz
    DBLP profile ↗ORCID search ↗
  14. MaxSup: Overcoming Representation Collapse in Label Smoothing
    NeurIPS 2025 ·
    Yuxuan Zhou
    DBLP profile ↗ORCID search ↗
  15. Medical Multimodal Model Stealing Attacks via Adversarial Domain Alignment
    AAAI 2025 ·
    Yaling Shen
    DBLP profile ↗ORCID search ↗
  16. Pixel-level Certified Explanations via Randomized Smoothing
    ICML 2025 ·
    Alaa Anani
    DBLP profile ↗ORCID search ↗
  17. Stealix: Model Stealing via Prompt Evolution
    ICML 2025 ·
    Zhixiong Zhuang
    DBLP profile ↗ORCID search ↗
  18. Adaptive Hierarchical Certification for Segmentation using Randomized Smoothing
    ICML 2024 ·
    Alaa Anani
    DBLP profile ↗ORCID search ↗
  19. Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation
    NeurIPS 2024 ·
    Sahar Abdelnabi
    DBLP profile ↗ORCID search ↗
  20. Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition
    NeurIPS 2024 ·
    Edoardo Debenedetti
    DBLP profile ↗ORCID search ↗
  21. Inside the Black Box: Detecting Data Leakage in Pre-Trained Language Encoders
    ECAI 2024 ·
    Yuan Xin
    DBLP profile ↗ORCID search ↗
  22. LLM Task Interference: An Initial Study on the Impact of Task-Switch in Conversational History
    EMNLP 2024 ·
    Akash Gupta
    DBLP profile ↗ORCID search ↗
  23. Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior Models
    NeurIPS 2024 ·
    Hui-Po Wang
    DBLP profile ↗ORCID search ↗
  24. MultiMax: Sparse and Multi-Modal Attention Learning
    ICML 2024 ·
    Yuxuan Zhou
    DBLP profile ↗ORCID search ↗
  25. On Adversarial Training without Perturbing all Examples
    ICLR 2024 ·
    Max Maria Losch
    DBLP profile ↗ORCID search ↗
  26. PoLLMgraph: Unraveling Hallucinations in Large Language Models via State Transition Dynamics
    NAACL 2024 ·
    Derui Zhu
    DBLP profile ↗ORCID search ↗
  27. SimSCOOD: Systematic Analysis of Out-of-Distribution Generalization in Fine-tuned Source Code Models
    NAACL 2024 ·
    Hossein Hajipour
    DBLP profile ↗ORCID search ↗
  28. Stealthy Imitation: Reward-guided Environment-free Policy Stealing
    ICML 2024 ·
    Zhixiong Zhuang
    DBLP profile ↗ORCID search ↗