Network Intrusion Detection with Neo4j and Snowflake
Chapters 9
- Play from Introduction & Guest Welcome
- Play from The Problem: IoT Network Intrusion Detection
- Play from How KNN & GraphSAGE Work Together
- Play from KNN Explained: Similarity-Based Graph Construction
- Play from Neo4j Graph Analytics on Snowflake: Architecture Overview
- Play from Demo Setup: The IoT Network Dataset
- Play from Step 1: Running KNN to Build the Similarity Graph
- Play from Step 2: Training GraphSAGE for Intrusion Classification
- Play from Step 3: Heterogeneous Graph with IP
Building a network intrusion detector with Neo4j Graph Analytics for Snowflake. We use KNN to connect similar attack events, then train GraphSAGE on those relationships to classify malicious traffic - all natively in Snowpark Container Services. We'll match the academic benchmark (macro-F1 0.811) using nothing but SQL.
Guests: Olga Razvenskaia ( linkedin.com/in/olga-razvenskaya (opens in a new tab) ) & Stu Moore ( linkedin.com/in/stujamesmoore (opens in a new tab) )
@SnowflakeInc
Resources mentioned
Cloud & data platforms
- Watched Duration: 25:20
- Watched Duration: 28:47
- Watched Duration: 11:11
- Watched Duration: 26:06
- Watched Duration: 11:39
- Watched Duration: 1:19:45
- Watched Duration: 7:29
- Watched Duration: 3:25
