LATIDIA · Ciberseguridad

SELF: A Robust Singular Value and Eigenvalue Approach for LLM Fingerprinting

arXiv:2512.03620v2 Anuncio Tipo: reemplazar Resumen: Salvaguardar la propiedad intelectual (PI) de los grandes modelos de lenguaje (LLM) contra el robo de modelos representa un desafío crítico en la investigación contemporánea de IA. Aunque fi

La noticia

arXiv:2512.03620v2 Announce Type: replace Abstract: Safeguarding the Intellectual Property (IP) of Large Language Models (LLMs) against model theft represents a critical challenge in contemporary AI research. Although fingerprinting is essential for establishing forensic evidence for model derivation, existing methods are susceptible to false claim attacks, weight manipulations, or high false positive rates, undermining their utility. To overcome these limitations, we propose SELF, \rev{a novel intrinsic weight-based fingerprinting scheme tailored for robust IP forensics via adversarial model lineage verification}. SELF eliminates dependency on input and inherently resists false claims, achieving robust \rev{provenance detection} through unique, scalable and transformation-invariant fingerprint extraction via singular value and eigenvalue decomposition of LLM attention weights. Experimental