Federated vs. Centralized Language Model Alignment Under Adversarial Perturbations

Abstract

Abstract: This report synthesises findings from 15 peer-reviewed papers addressing the following research question: How do alignment metrics for federated language models degrade under adversarial perturbations compared to centralized models when measured on safety evaluation datasets. Current research in adversarial robustness of LLMs focuses on discrete input manipulations in the natural language space, which can be directly transferred to closed-source models. However, this approach neglects the steady progression of open-source models. 9 claims were extracted from source literature; 0 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 3.2/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research Question

How do alignment metrics for federated language models degrade under adversarial perturbations compared to centralized models when measured on safety evaluation datasets?

Verification Level

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Quality Tier

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance