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.
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.
30 articles. Page 3 of 5.
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
Modalis: Prototype Exchange for Heterogeneous Multimodal DFL
How Modalis works: multimodal prototypes, gating and alignment in DFL. Published results, limitations and proposed ablations.
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 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
Flighter: Situational Awareness as a Reliability Signal in DFL
How Flighter combines context and models to evaluate DFL reliability: study scope, indicator ablations and participant recovery.