paperAugust 2026Unreviewed

Quantization-Triggered Backdoors in Language Models: Cross-Quantizer Transferability and the Validation--Deployment Gap

Jacopo Dardini, Claudio Stanzione, G. Colò, G. Fenza

Abstract

Post-training quantization is often treated as a semantically neutral optimization for edge deployment of Large Language Models. When a full-precision source checkpoint is evaluated and quantization is applied downstream without equivalent re-evaluation, this workflow creates a structural validation--deployment gap: because quantization is a many-to-one mapping over parameter space, source-precision certification does not guarantee behavioral equivalence in the deployed configuration. We formali

Framework mappings

OWASP Top 10 for LLM Applications

LLM04Data and Model Poisoning

MITRE ATLAS

AML.T0020Poison Training Data

Suggested from the entry's categories.

Cite

@misc{dardini2026quantizationtriggered,
  title = {{Quantization-Triggered Backdoors in Language Models: Cross-Quantizer Transferability and the Validation--Deployment Gap}},
  author = {Jacopo Dardini and Claudio Stanzione and G. Colò and G. Fenza},
  year = {2026},
  month = aug,
  eprint = {2608.27512},
  archivePrefix = {arXiv},
  url = {https://www.semanticscholar.org/paper/4814c6bd8be0dc62cbee06a2fb1d391b5cfc7191}
}