Language Model Fingerprinting Requires Rethinking Watermark Teachers
cs.CR, cs.AI
Submitted: 2026-10-03
Updated: 2026-10-03
Terminology
Sources
- Model Equality Testing: Which Model Is This API Serving?
- The Lucie-7B LLM and the Lucie Training Dataset: Open resources for multilingual language generation
- BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
- Robust Distortion-free Watermarks for Language Models
- Adaptive Text Watermark for Large Language Models
- Deep Neural Network Fingerprinting by Conferrable Adversarial Examples
- Large Language Models: A Survey
- Are Robust LLM Fingerprints Adversarially Robust?
- Qwen2.5 Technical Report
- SLIP: Securing LLMs IP Using Weights Decomposition
- Hey, That's My Model! Introducing Chain & Hash, An LLM Fingerprinting Technique
- FIT-Print: Towards False-claim-resistant Model Ownership Verification via Targeted Fingerprint
- RAFP: Identifying LLM Lineages via Rare-Region Fingerprints
- FPEdit: Robust LLM Fingerprinting through Localized Parameter Editing
- Organize the Web: Constructing Domains Enhances Pre-Training Data Curation
- The Model Openness Framework: Promoting Completeness and Openness for Reproducibility, Transparency, and Usability in Artificial Intelligence
- Optimizing watermarks for large language models
- ImF: Implicit Fingerprint for Large Language Models
- EditMF: Drawing an Invisible Fingerprint for Your Large Language Models
- SRAF: Stealthy and Robust Adversarial Fingerprint for Copyright Verification of Large Language Models
Related papers
- SoK: AI-Augmented Binary Reversing
- Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
- Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills
- Token Composition: A Graph Based on EVM Logs