Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/jazbengu/ThreatDetect/llms.txt

Use this file to discover all available pages before exploring further.

ThreatDetect is an AI-powered platform that analyzes employee behavioral data to surface insider threats. Built on XGBoost with Isolation Forest anomaly scoring, it provides both batch organizational analysis and individual employee risk scoring — with SHAP-driven explanations so you always know why a prediction was made.

Quickstart

Get ThreatDetect running and analyze your first dataset in minutes.

How it works

Understand the detection pipeline: features, model, scoring, and explainability.

CSV batch analysis

Upload an organizational CSV and detect threats across your entire workforce.

Input data schema

Learn exactly which columns your data must contain for accurate predictions.

What ThreatDetect does

ThreatDetect combines machine learning with human-readable explanations to give security teams actionable intelligence — not just a list of flags.

Batch organizational scan

Upload a CSV of employee records, run detection, and download results with risk scores for every person.

Single employee lookup

Run a targeted analysis on one employee and see per-feature SHAP explanations driving their risk score.

Explainable predictions

Every prediction comes with SHAP values showing which behavioral features pushed toward malicious vs. normal.

Exploratory data analysis

Explore your dataset interactively — distributions, correlations, scatter plots, and quick anomaly scans.

Get started in three steps

1

Install dependencies

Clone the repository and install Python requirements with pip install -r requirements.txt.
2

Launch the app

Run streamlit run streamlit_app.py to open ThreatDetect in your browser.
3

Upload your data

Navigate to Organisational Search via CSV, upload a CSV with the required columns, and click Run Threat Detection.
ThreatDetect requires Python 3.8+ and the pre-trained model file at AI_Model_Code/insider_threat_model.pkl. See the installation guide for full setup instructions.

Build docs developers (and LLMs) love