The Security of Amazon Go

The Security of Amazon Go

The convenience store of the future has some hefty security.

Yesterday Amazon's first brick-and-mortar convenience store, opened its doors. Amazon Go is a 1,800 square-foot mini-market packed with shelves of items you would commonly find at a the corner store, but Amazon took the idea of "convenience" and made it, well, more convenient.

The new Amazon Go store has no lines and no cashiers and touts the fact that all you have to do is literally grab what you need and go. But how does it work? With Amazon's "Just Walk Out Technology," which is basically just a bunch of security measures.

Here's the breakdown on the security inside Amazon Go:

The first thing you are greeted by at the front door is a row of three turnstiles, which are activated by using a unique QR Code found in the Amazon Go app. These turnstiles keep those who are not set up with the Amazon Go app out of the store while letting those who have downloaded the app and linked it to their Amazon account in. These turnstiles are what register what users are in the store and when they leave.

When a user enters the store, the are encouraged to pick up and put back as many items as they want. When an item is picked up, the store automatically adds it to the user's virtual shopping cart. If it is returned to the shelf, it will be removed from the online shopping cart. When the shopper leaves the store, they usually receive a receipt of their purchase within just a couple minutes.

The ceiling of the store is covered with cameras that watch your every move while you are in the store. Using the QR code you scanned at the turnstile, the cameras can help register which user is picking up what item. The cameras work in tandem with the turnstiles to ensure what you left the store with is what you are paying for.

Amazon won't say much more about how this video surveillance system works, other than to say it involves sophisticated computer vision and machine learning software. This means that there isn't any tracking chips on the merchandise in the store. It is the placement of items on the shelves and the cameras in the ceiling that keeps track of who picked up what.  

Some reporters have attempted, with the permission of Amazon, to shoplift from the store. The New York Times' Nick Wingfield wrote that he attempted to steal a four-pack of vanilla soda while wrapping it with a shopping bag with it was still on the shelf and then tucking it under his arm while walking out of the store. His experiment failed and minutes later, he received a notification that he'd been charged for the soda.

About the Author

Sydny Shepard is the Executive Editor of Campus Security & Life Safety.

Featured

  • It's Show Time

    I am one of those people that likes to see things get bigger and better. As advertised, ISC West is going to be bigger (more exhibitors) and better (more attendees). It’s show time in Las Vegas. Read Now

    • Industry Events
    • ISC West
  • SIA Releases New Report on Operational Security Technology

    The Security Industry Association (SIA) has released an impactful new resource – Operational Security Technology: Principles, Challenges and Achieving Mission-Critical Outcomes Leveraging OST. Read Now

  • Cyber Overconfidence Is Leaving Your Organization Vulnerable

    The increased sophistication of cyber threats pumped by the relentless use of AI and machine learning brings forth record-breaking statistics. Cyberattacks grew 44% YoY in 2024, with a weekly average of 1,673 cyberattacks per organization. While organizations up their security game to help thwart these attacks, a critical question remains: Can employees identify a threat when they come across one? A Confidence Gap survey reveals that 86% of employees feel confident in their ability to identify phishing attempts. But things are not as rosy as they appear; the more significant part of the report finds this confidence misplaced. Read Now

  • Mission 500 Debuts Refreshed Identity Ahead of Security 5K/2K at ISC West

    Mission 500, the security industry’s nonprofit charity dedicated to supporting children in need across the US, Canada, and Puerto Rico, has unveiled a refreshed brand identity ahead of ISC West. The charity’s new look includes a modernized logo with refined messaging to reinforce Mission 500’s nearly decade-long commitment to serving the needs of children and families in crisis. Read Now

    • Industry Events

New Products

  • Hanwha QNO-7012R

    Hanwha QNO-7012R

    The Q Series cameras are equipped with an Open Platform chipset for easy and seamless integration with third-party systems and solutions, and analog video output (CVBS) support for easy camera positioning during installation. A suite of on-board intelligent video analytics covers tampering, directional/virtual line detection, defocus detection, enter/exit, and motion detection.

  • ResponderLink

    ResponderLink

    Shooter Detection Systems (SDS), an Alarm.com company and a global leader in gunshot detection solutions, has introduced ResponderLink, a groundbreaking new 911 notification service for gunshot events. ResponderLink completes the circle from detection to 911 notification to first responder awareness, giving law enforcement enhanced situational intelligence they urgently need to save lives. Integrating SDS’s proven gunshot detection system with Noonlight’s SendPolice platform, ResponderLink is the first solution to automatically deliver real-time gunshot detection data to 911 call centers and first responders. When shots are detected, the 911 dispatching center, also known as the Public Safety Answering Point or PSAP, is contacted based on the gunfire location, enabling faster initiation of life-saving emergency protocols.

  • QCS7230 System-on-Chip (SoC)

    QCS7230 System-on-Chip (SoC)

    The latest Qualcomm® Vision Intelligence Platform offers next-generation smart camera IoT solutions to improve safety and security across enterprises, cities and spaces. The Vision Intelligence Platform was expanded in March 2022 with the introduction of the QCS7230 System-on-Chip (SoC), which delivers superior artificial intelligence (AI) inferencing at the edge.