PREDATOR - Proactive Recognition and Elimination of Domain Abuse at Time-Of-Registration

Explore a conference talk from CCS 2016 that delves into PREDATOR, a system for proactively recognizing and eliminating domain abuse at the time of registration. Learn about the challenges of domain abuse in practice, including batch registration and domain reuse techniques. Examine the methodology for ground truth labeling, raw data analysis, and feature extraction from registration history and batch correlations. Discover the detection performance, latency measurements, and evasion robustness of the PREDATOR system. Gain insights into key results for registration detection and its implications for improving cybersecurity measures against malicious domain registrations.

Intro
Domain Abuse in Practice
Case Study Introduction
Lazy: Batch Registration
Parasitic: Domain Reuse
Ground Truth Labeling Errors
Raw Data Overview
Registration History Features
Batch Correlation Features
Feature Vectorization
Detection Performance
Detection Latency Measurement
Evasion Robustness
PREDATOR Key Results Registration Detection