5 min readResearch note
Robust Decentralized Federated Learning: Limits and Open Questions
Open questions in robust DFL: dynamic graphs, manipulated context, privacy, missing modalities and experiments to test the limits.
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.
Topic: Trustworthy AI Clear topic
9 articles. Page 1 of 2.
4 min readGuide
Large Language Models for Cybersecurity: A Careful Starting Point
LLMs for cybersecurity: SOC use cases, evidence, permissions and evaluation. Move from summarization to a tool-using assistant.
3 min readResearch note
Parametric RAG: Moving Security Knowledge Into the Model
P-RAG versus contextual RAG: parametric memory, updates, permissions and provenance for cybersecurity knowledge.
3 min readGuide
Mixture of Experts in LLMs: Capacity Through Selective Routing
How MoE LLMs work: routing, active parameters, memory, load balance and latency and quality evaluation across languages.
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.