Beginning of July, U.S. Customs and Border Protection (CBP) officials inspected five shipments of what were apparently Apple AirPods shipped from China. In what is now a routine occurrence, agents in Cincinnati (presumably working out of the UPS hub in Louisville, although this is not specified) suspected something was wrong.

Whether it was the packaging, the declared value of $ 1,872 or the destination address of Brownsville, Texas, convenient for the cartel smugglers, they flagged the shipment and sent the manifesto and photographs to specialists at a CBP center designed to spot counterfeits. Instead of nearly 6,400 AirPods and AirPods Pro models valued at over $ 1.3 million retail, they found counterfeit valued at $ 312.

The seizure of Cincinnati is just the tip of a huge iceberg of fake consumer electronics, clothing, shoes and jewelry. Due to their high value for money, AirPods and other high-end headphones have become particularly lucrative for counterfeiters. Indeed, already this year, the CBP seized approximately 360,000 counterfeit wireless headphones valued at over $ 62 million, 25 times more than in 2019.

International e-commerce has been a boon for consumers, who have access to otherwise unavailable products, and for crooks who use sites like AliExpress, JD.com, Facebook, Amazon, and Tokopedia to distribute their fake wares. CBP statistics show the increase in these counterfeits going directly to consumers via a significant increase in the number of small parcels seized over the past decade, most of them coming from the post office. In the preface of a United States Department of Homeland Security (DHS) Report 2020 Combating Trafficking in Counterfeit and Pirated Goods Then-secretary Chad Wolf wrote that:

Illicit goods delivered to U.S. consumers through e-commerce platforms and online third-party marketplaces threaten public health and safety, as well as national security. This illicit activity is impacting American innovation and eroding the competitiveness of American manufacturers and workers. Consumers must have confidence in the safety, quality and authenticity of the products they buy online.

Whether measured in potential value or in number, nearly all of the counterfeits seized by CBP originate in China. Although 80% of the items are jewelry or clothing, CBP confiscated more than $ 100 million in fake consumer electronics in 2019, with some sales estimates for fake AirPods to over $ 350 million per month. Indeed, the OECD estimates that counterfeit products now represent 3.3% of world trade.

Outsmarting counterfeiters with blockchain

Blockchain has long seemed like a technology looking for a problem, but as I detailed earlier this year when describing the features added to the Oracle database, Blockchain immutability has many applications in it. securing and auditing corporate data. The fight against counterfeiters is one area where blockchain could come in handy by creating a permanent record of items as they move through the supply chain.

Manufacturers have long used barcodes to automate the identification of item numbers during distribution and in point-of-sale systems. Unfortunately, traditional UPC tags do not support item-level identifiers and can be easily tampered with. On the other hand, the most recent GS1 Global Trade Item Numbers (GTIN) serialization support to uniquely identify individual items. As Auburn University RFID Lab Report Details, SGTINs can be encoded on paper as QR codes or 2D data matrices and electronically in the form of RFID or NFC tags and automatically read using image or RF scanners.

While SGTIN is a way to uniquely mark and automatically identify individual items, the blockchain provides a mechanism to reliably and irrefutably track items as they move through the supply chain. Here’s how the Auburn report sees the combination of unique identifiers and blockchain used to fight counterfeit products.

“With blockchain, brands can fight counterfeiting by maintaining immutable records of all products ordered and sharing item-level details with sellers and consumers to ensure product authenticity. … by documenting and by distributing the identity of legitimate products, a brand owner can crack down on counterfeit products produced upstream and complement product verification efforts with retail partners and downstream customers. By using item-level information to reinforce data-driven decisions, illegitimate distribution channels can be identified and bad actors can be separated from the supply network.

He also sees the blockchain distributed ledger used to resolve disputes over product legitimacy between buyers and sellers:

In a blockchain ecosystem where brand owners and retailers exchange item-level data related to shipping and orders, disputes can be settled with hard data and resolutions can be expedited as both parties refer to the same source of information made available by the distributed ledger.

Blockchain-based product traceability at the item level can also improve:

• Food and drug safety by identifying particular items suspected of contamination and reporting bogus or gray market products.
• Settlement of claims regarding shipping errors and incorrect fulfillment of orders.
• Lost inventory or reduction of products by minimizing ambiguity or intentional deception in business processes.
• Supplier audits and dashboards by providing indisputable proof of on-time delivery and product origin.

Products Consensys, SAP and Vi3 now integrate blockchain technology to reduce distribution and automate the identification of counterfeit products.

Using AI to spot counterfeits

The overt (QR codes, RFID tags) and covert (microscopic taggants, non-cloning physical functions, aka PUF) use to verify product authenticity is effective, but can be costly or impractical for unpackaged products like clothing or jewelry. High-resolution image analysis using AI models is an alternative increasingly used by fashion retailers and manufacturers. Pioneer by startups like Entrupia, the process combines machine learning, computer vision, and a huge database of genuine and counterfeit product images.

For example, the Entrupy system uses a high resolution camera that magnifies images at least 100 times to expose product characteristics such as fabric, texture and finish in much more detail than you might think. the human eye. Then, just like facial recognition systems such as Apple FaceID, the system creates a digital ID of an original item using 500 to 1,500 features. Individual items are then compared against this digital fingerprint to verify their authenticity and report counterfeits.

From a paper detailing the technique, the Entrupy system has several advantages over conventional marking (added emphasis):

We don’t need to incorporate any substance into the product or the object. Our technique is non-invasive and does not modify the object in any way. ii) It is not necessary to label each item. We can classify the original and duplicate it based on microscopic variations. iii) Current manifest / disguised authentication techniques cannot authenticate objects that have not been previously marked. In our case, since we are using machine learning techniques, we can authenticate new instances of the object. iv) Most techniques such as nano-printing and micro-labels are expensive to integrate into the product. Plus their detection based on specialized and expensive microscopic handheld devices which is a problem in consumer / business adoption. Our device-based, cloud-based authentication solution that works with a mobile phone is inexpensive and easy to use.

My opinion

Counterfeits represent both a significant risk to the brand’s reputation and an increasing cost due to lost revenue. Given that clothing is the primary target for fake products, it’s no surprise that high-profile and luxury brands like Calvin Klein, Chanel, Gucci, Levi’s, Lululemon, and Nike are already using technologies like RFID tags and AI image recognition to verify legitimate products and block counterfeiters. .

Amazon Zero Project is perhaps the most ambitious project to eliminate counterfeits by allowing brands to label each unit with a unique code, shared with Amazon, which allows it to scan and confirm the authenticity of every listed product sold through the Amazon store. While Amazon appears to be using a centralized database rather than a distributed blockchain ledger, expect manufacturers to investigate blockchain as they seek out a widespread product verification system that works throughout. their supply chain.