3 min readResearch note
D-MoE: Distributed Mixture of Experts for Edge LLMs
Distributed MoE at the edge: expert placement, critical-path latency, bandwidth, activations and failure recovery.
Research Notes on Federated Learning, Cybersecurity and Cyberdefense
Research notes and technical guides on federated learning, distributed AI, cyberdefense, trustworthy systems, and privacy-preserving platforms.
16 articles. Page 2 of 3.
3 min readGuide
Golden Sets for LLM Evaluation: Small, Curated and Difficult to Cheat
Build golden sets for LLMs and RAG with examples, adjudication, leakage-aware splits and bilingual security cases.
3 min readGuide
Metrics for LLMs, RAG and Cybersecurity Systems
LLM and RAG metrics: retrieval recall, citations, unsafe actions, calibration, latency and uncertainty. Define fair comparisons.
5 min readResearch note
Communication Efficiency in DFL: Why Prototypes Matter
Compare models and prototypes in DFL: message size, cumulative bytes, quantization and target quality under network constraints.
5 min readResearch note
When Federated Clients See Different Modalities
Multimodal federated learning with non-IID data and missing sensors: masks, prototypes and evaluation by modality and client.
5 min readGuide
Designing a Decentralized Federated Learning System
Design a DFL system with topology, message contracts, mixing weights, recovery policies and per-client evaluation.