{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/023ffd1704bc41b6b27f2da8cb06953e\" frameborder=\"0\" width=\"1920\" height=\"1440\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1440,"width":1920,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1440,"thumbnail_width":1920,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/023ffd1704bc41b6b27f2da8cb06953e-c83150270abcee28.gif","duration":300.12,"title":"Counter Sign: Detecting Fake Bills Automatically","description":"This Loom explains a project called Counter Sign that automatically checks invoices for fake bills to prevent fraud. Akmal notes that in 1995 companies in the US lost over $3 billion to counterfeit bills, a problem that has been rising, often because startups or employees trust invoices without verifying them. The system pulls bills every two minutes from Gmail or accepts manual or CLI uploads, then runs about 14 small checkers to compute a score and classify results as clear, not clear, or requiring human attention, dropping documents if the score is too low. Checks include email and company matching, amount anomaly such as changes over 67 percent from a baseline, look alike indicators like altered domains, and bank number and document history analysis."}