I built my first open-source project: Chickadee Studio — a desktop tool for detecting hidden and disguised advertising on websites

Description and use

Chickadee Studio is a desktop app that scans web pages, extracts text from images, analyzes DOM/CSS, detects text obfuscation, and uses local ML models to identify hidden advertising, offering screenshots for manual review.

Problem

Advertising can be hidden or disguised using look‑alike characters, Unicode tricks, images, or hidden HTML, making simple keyword matching ineffective.

Outcome

The tool provides a local, end‑to‑end pipeline that detects hidden or disguised advertising, offering visual evidence for manual review and supporting AI assistance.

Workflow

• Scan target webpage or content
• Extract text from images using PaddleOCR
• Analyze DOM elements and CSS for hidden content
• Detect text obfuscation techniques
• Apply local ML models to classify advertising context
• Generate screenshots and evidence for manual review
• Optionally use AI‑assisted analysis

Evidence

It's a desktop application I built to help identify potentially hidden or disguised advertising in website content, including posts, comments, and images.

Source

Uses OCR (PaddleOCR) to extract text from images

Source

Analyzes DOM elements and CSS for potentially hidden content

Source

Detects text obfuscation techniques

Source

Uses local ML models to help identify advertising context

Source

Provides screenshots and evidence for manual review

Source

Supports optional AI-assisted analysis

Source