Insider Threat Detection & Automation by Behaviour Analytics
summary
Claims that user and entity behavior analytics (UEBA) uses supervised and unsupervised machine learning to baseline normal activity and emit a risk score for deviations. Gives concrete detections: huge multi‑gigabyte uploads flagged by volumetric analysis, simultaneous logins from different countries and service‑account misuse via pair-based anomaly detection. Cites sector rates (pharma ~28.3%, banking ~27.7%, IT ~13.2%) and links to real incidents like the Twitter employee compromise; describes automated alerts and log‑source inputs and asserts the model successfully surfaces true insider threats.
AI-written summary · about
chapters (17)
- 0:00Introduction
- 0:21About Hima
- 1:40Disclaimer
- 1:56Case Study
- 3:02What is Insider Threat Detection
- 3:58Why Insider Threat Detection
- 5:18Types of Insiders
- 8:38What is UEBA
- 10:25Anomalies
- 12:38Volumetric Analysis
- 13:31Statistics
- 15:01Use Cases
- 17:33Identity Theft
- 18:29Models
- 19:06Data Analytics
- 20:38Technology
- 22:12Summary
related talks
15mSecret Tips to Reduce Insider Threat Risks with Behavioral AI
21mBusiness Defence -- Managing the Insider Threat with Security Analytics
01h 01mD1T2 - Applying Machine Learning to User Behavior Anomaly Analysis
16mAI-Driven Behavioral Analytics for Real-Time Fraud Prevention
54mInsider Threats and New Economy Industries
13mBehavioral Analytics for Real-Time Fraud Prevention
39mDetecting Website Intrusion and Account Compromise with Machine Learning
29mThresholds Are for Old Threats: Demystifying AI and Machine Learning to Enhance SOC Detection