AI Powered Authentication

Entrupy’s machine learning algorithms are trained on a rich and diverse data set of millions of microscopic images. With the introduction of sneakers we've also built a rich data of macroscopic images as well. This unparalleled data set continues to grow in real time with every verification performed. Pinpoint accuracy is a by-product of our intelligent network driven solution with objectivity built in, eliminating human bias in the verification process. Speed, with many results are issued instantly, is enabled by our AI powered authentication engine running securely on Cloud.

Components of our solution

Highly Secure, Highly accurate and built for scale
  • Portable Device that magnifies the images 260x with uniform lighting
  • An iOS mobile app for capturing high resolution microscopic images
  • A secure, authentication service on Cloud
  • 256 bit encryption to secure Edge to Cloud control and data traffic
  • State of the art AI algorithms to detect and classify counterfeits

Data and Algorithms: Foundations of Our Authentication Solution

We utilize high quality data collected to train our algorithms to differentiate between fake and authentic items, which in turn, gives us the ability to produce results like our 99.1% accuracy rate. Every item that’s authenticated helps the algorithms learn and improve, creating a smarter solution that adapts to the changing world.

Our data

Our data teams have collected millions of images from a variety of categories of physical goods (bags & accessories, shoes, watches) through data partnerships with the most prominent and trustworthy businesses from around the world to create our rich, diverse, and unmatched data-set.

Data Quality

We take utmost care in ensuring our data meets the highest standard of quality. We run 3 different layers (2 manual verifications and one algorithmic) of filtering that allows us to correct any possible errors in the data submitted. This ensures that the algorithms are always fed extremely high quality information during the machine-training process.

Data Processes

We have data points from over 80 years ago all the way up to recent months, which enables us to provide technology based authentication services for a wide time range for the brands we support. In general we support most styles and materials produced by a particular brand. Our data teams keep track of recent releases from brands and try to incorporate them into our algorithms as soon as possible to give our customers immediate access to contemporary styles.

Check out this paper published by the founders of Entrupy to learn more about the technology powering our authentication system.

The Fake vs Real Goods Problem: Microscopy and Machine Learning to the Rescue

Ashlesh Sharma (Entrupy Inc);   Vidyuth Srinivasan (Entrupy Inc);   Vishal Kanchan (Entrupy Inc);   Lakshminarayanan Subramanian (Entrupy Inc)

Entrupy published on

“We introduce a new mechanism that uses machine learning algorithms on microscopic images of physical objects to distinguish between genuine and counterfeit versions of the same product. The underlying principle of our system stems from the idea that microscopic characteristics in a genuine product or a class of products (corresponding to the same larger product line), exhibit inherent similarities that can be used to distinguish these products from their corresponding counterfeit versions. A key building block for our system is a wide-angle microscopy device compatible with a mobile device that enables a user to easily capture the microscopic image of a large area of a physical object. Based on the captured microscopic images, we show that using machine learning algorithms (ConvNets and bag of words), one can generate a highly accurate classication engine for separating the genuine versions of a product from the counterfeit ones; this property also holds for super-fake counterfeits observed in the marketplace that are not easily discernible from the human eye. We describe the design of an end-to-end physical authentication system leveraging mobile devices, portable hardware and a cloud-based object verication ecosystem. We evaluate our system using a large dataset of 3 million images across various objects and materials such as fabrics, leather, pills, electronics, toys and shoes. The classication accuracy is more than 98% and we show how our system works with a cellphone to verify the authenticity of everyday objects.

To download and read the complete paper, please click here.