All Topics
All Topics
Technology
Technology
Design
Design
Programming
Programming
Science
Science
News
News
Gaming
Gaming
Entertainment
Entertainment
Business
Business
Finance
Finance
Sports
Sports
Health
Health
Food
Food
Travel
Travel
Art
Art
Music
Music
Books
Books
Education
Education
Politics
Politics
Personal
Personal
No algorithm. No AI slop. No ads. Just RSS. Pro-human. Indie writers. Real journalism. Open web. Chronological. Hand toasted.

SHIBUYA WAF: Open-Source Web Application Firewall with Machine Learning and eBPF Security

By

germainluperto

3mo ago· 2 min readenNews

Summary

SHIBUYA WAF is a next-generation open-source web application firewall that combines traditional rule-based security with machine learning and eBPF kernel-level blocking. It features a dual ML engine with explainable AI using SHAP to detect and classify attacks across 10 categories including SQLi, XSS, RCE, and others. The system includes 615+ OWASP CRS rules, GraphQL/API protection, WASM plugins, and a built-in attack lab for testing.

Key quotes

· 4 pulled
Dual ML Engine with SHAP Explainability: Two independent ML models run in parallel: an IsolationForest (via ONNX runtime) detects anomalies, and a Random Forest classifies attacks across 10 classes
SHAP-like explainability shows exactly which top-5 features triggered the alert. Human-in-the-loop feedback loop. A/B model testing. Data drift detection
Next-gen open-source WAF. ML detection with explainability. eBPF kernel blocking. 615+ CRS rules. GraphQL/API protection. WASM plugins. Built-in attack lab
Cloudflare doesn't want you to have this
Snippet from the RSS feed
Next-gen open-source WAF. ML detection with explainability. eBPF kernel blocking. 615+ CRS rules. GraphQL/API protection. WASM plugins. Built-in attack lab. Cloudflare doesn't want you to have this.

You might also wanna read