Open-source machine learning ad fraud detection for small businesses.
Detect click fraud and fake conversions from Google, Facebook, Instagram, and TikTok.
AdTruth is a free, open-source ad fraud detection tool designed to help small businesses identify click fraud and bot traffic. It uses machine learning to track visitor behavior and highlight which ad platforms waste your budget.
The tool tracks behavioral signals like mouse movements and scroll depth via a lightweight 12KB script installed on your website. Its ML models calculate fraud rates per platform, letting you compare channels and reallocate your budget to real customers.
It suits small business owners, e-commerce stores, and local businesses spending money on paid acquisition who cannot afford enterprise tools like CHEQ or ClickCease. It does not suit teams looking for automated server-side blocking rather than analytics and budgeting insights.
Identifies AI-powered bots that mimic human scrolling and mouse movements.
Compares fraud rates across Google Ads, Facebook, Instagram, and TikTok.
Runs on a 12KB asynchronous script that will not harm core web vitals.
Aggregates fraud patterns across participating sites to improve scoring accuracy.
AdTruth is free forever under its MIT license, with no paid hosted pricing tier mentioned in the README.
877 open remote AI-training roles, updated November 16, 2026; most pay $20–$175 an hour. Zekai lists them free; the application goes to the employer’s platform.
No, AdTruth is 12KB minified, loads asynchronously, and will not block page rendering or hurt Core Web Vitals.
Yes, it collects only anonymized behavioral signals with no personal information, emails, names, or passwords.
Yes, you can clone the repository, modify it, and self-host it yourself.
See Zekai first in Google