ConceptioArchiveZenodo (CERN)
Zenodo (CERN)open access

Measuring Backdoor Persistence in Post-trained Large Language Models: The Cyber Resilience Scaling Coefficient

Santanna Lopes, João Renan et al.
Zenodo (CERN) · Papers · License: Open Access
Open Source ↗
large-language-models
Large language models, data poisoning, back- door attacks, cyber resilience, supervised fine-tuning,, model robustness, security evaluation.
This document is indexed with metadata only — full text is not available in the archive for this record. Open the official source ↗
Record · ID 990470
Retrieved via Conceptio — every document is proof-bundled with source, license, and retrieval metadata.