4 min readGuide
Privacy, Secure Aggregation and Robustness in DFL
Combine differential privacy, secure aggregation and robust DFL with explicit trust assumptions, local threat budgets and joint evaluation.
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 1 of 5.
4 min readGuide
Prompt Injection in RAG and LLM Agents: A Security Evaluation Guide
Evaluate prompt injection in RAG and LLM agents with paired tests, permission checks, tool traces and recent benchmark research.
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.
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.
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.
4 min readGuide
LLM-Supported Attack Mitigation Without Unsafe Autopilot
LLM-assisted mitigation: playbooks, evidence, permissions, idempotency and recovery. Turn recommendations into verifiable actions.