arXiv (All)
open access
Component-Aware Differential Privacy for Federated Multilingual Speech-LLMs
Per-layer differential privacy (DP) clipping improves gradient fidelity in federated learning by allocating per-matrix clipping budgets proportional to parameter count. We show that this recipe breaks for speech large language models (speech-LLMs), when the acoustic encoder and the language decoder
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
- An Adaptive Gradient Clipping and Noise Injection Mechanism for Differentially Private Federated Learning#612579
- An Adaptive Gradient Clipping and Noise Injection Mechanism for Differentially Private Federated Learning#611102
- An Adaptive Gradient Clipping and Noise Injection Mechanism for Differentially Private Federated Learning#459586
- Differential Privacy for Deep and Federated Learning: A Survey#177275
- AEGIS: Attention-Embedding Gradient Isolation Shield - Triple-Channel Gradient Masking for Privacy-Preserving Federated LLM Fine-Tuning#471193
Record · ID 999450
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