arXiv (All)
open access
RAPTOR: Role-Aware Private Training for Mixture-of-Experts
Differentially private (DP) fine-tuning methods treat sparse Mixture-of-Experts (MoE) models as a single dense block, ignoring that shared layers see all data while experts only see routed records. We identify and formally characterize three resulting failure modes: global clipping suppresses expert
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- PRIVET: PRoximIty leakage detection Via Extreme value Theory#1035332
- Expert-Aware Causal Tracing of Factual Recall in Sparse MoE Language Models#926063
- Neither Adversarial Training Nor Purification: Emergent Adversarial Robustness from Oscillatory Predictive Learning#668059
- Data Privacy and traceability in Deep Learning#291817
- From Self-Supervised Speech Models to Mixture-of-Experts for Robust Anti-Spoofing#271873
Record · ID 972814
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive