New CO-DEFEND framework enables privacy-preserving DoH threat detection

Researchers have developed a new framework called CO-DEFEND to address the challenge of detecting malicious DNS over HTTPS (DoH) traffic while preserving data privacy. This decentralized federated learning approach allows multiple entities to collaboratively train machine learning models in real-time without sharing their sensitive local data. The framework adapts common machine learning algorithms like Support Vector Machines, Logistic Regression, Decision Trees, and Random Forest for this federated environment, demonstrating effectiveness in threat detection with improved scalability and efficiency compared to existing methods. AI

IMPACT Enhances privacy-preserving capabilities in network security threat detection systems.

RANK_REASON Academic paper detailing a new framework and methodology for machine learning. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• CIRA-CIC-DoHBrw-2020
• CO-DEFEND
• decision tree
• Diego Cajaraville-Aboy
• DNS over HTTPS
• logistic regression model
• machine learning
• random forest
• support vector machine

• paper
• safety
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →