A three-stage LLM fingerprinting pipeline (multilingual low-perplexity triggers, edit-based injection with adversarial suppression, and subspace-aware fine-tuning regularization) reports robust and persistent ownership markers.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
From Construction to Injection: Edit-Based Fingerprints for Large Language Models
A three-stage LLM fingerprinting pipeline (multilingual low-perplexity triggers, edit-based injection with adversarial suppression, and subspace-aware fine-tuning regularization) reports robust and persistent ownership markers.