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
7 articles. Page 1 of 2.
4 min readResearch note
Autonomous Cyberdefense Needs More Than an LLM
Autonomous cyberdefense with LLMs: control states, action boundaries, recovery and separate evaluation of utility and safety.
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.
5 min readResearch note
How to Measure Robustness in Adversarial DFL Experiments
Evaluate DFL robustness with F1, false rejection, overhead and recovery. Interpret Flighter and compare clean and attacked conditions.
5 min readResearch note
From Monitoring to Mitigation: A DFL Cyberdefense Lifecycle with LLM Explanations
Connect telemetry, federated learning, alerts and LLM-assisted mitigation with traceable evidence, validation and reviewed feedback.
3 min readResearch note
Byzantine-Resilient Aggregation for Decentralized Federated Learning
Median, trimmed mean and trust in DFL: examples, local poisoning assumptions and defense costs with legitimate non-IID clients.