RFID tags are commonly used to verify the authenticity of products, but they have some drawbacks. They are relatively large, expensive, and vulnerable to counterfeiting. A team of MIT engineers has developed a new type of ID tag that overcomes these limitations by using terahertz waves, which are smaller and faster than radio waves.
The new tag is a cryptographic chip several times smaller and cheaper than RFID tags. It also offers improved security, using the unique pattern of metal particles in the glue that attaches the tag to the item as a fingerprint. This way, the authentication system will detect tampering if someone tries to peel off the tag and stick it to a fake item.
- New technique can spy on your security cameras through walls
- How AI and RFID could solve the surge in lost airport luggage
- New tech could transform phones into RFID readers
The tag was invented a few years ago by the same MIT researchers, but it had a major flaw: it shared the same security vulnerability as RFID tags, as it could be easily removed and reattached. The engineers have now solved this problem by adding the antitampering feature, which leverages the properties of terahertz waves.
How terahertz waves work as a security tool
Terahertz waves are electromagnetic waves between microwaves and infrared light on the spectrum. They have advantages over radio waves, such as higher bandwidth, higher resolution, and lower power consumption. They can also penetrate through materials blocking other wave types, such as clothing, paper, and plastic.
MIT engineers have developed an anti-tampering ID tag that uses terahertz waves to verify the authenticity of an item. The tag has tiny slots that allow terahertz waves to pass through and reach the glue layer that sticks the tag to the item. The glue layer contains microscopic metal particles that act as mirrors for terahertz waves, reflecting them to the tag in a random pattern, explains Eunseok Lee, an electrical engineering and computer science (EECS) graduate student and lead author of a paper on the antitampering tag. The tag reads the reflected pattern and converts it into a digital code that represents the fingerprint of the item. The code is then compared with a database of registered fingerprints to authenticate the item.
The engineers demonstrated the effectiveness of their antitampering tag by producing a light-powered chip about 4 square millimeters in size. They also developed a machine-learning model to identify similar glue patterns with more than 99% accuracy.
How the tag prevents tampering
The tag's antitampering feature destroys the glue layer when peeled off, which alters the metal particles' pattern and corresponding terahertz signal. Multiple slots on the chip capture more information on the random distribution of particles. The unique responses cannot be duplicated if the glue interface is destroyed. Vendors can take an initial reading of the tag and store the data in the cloud for later verification.
How AI helps with authentication
But when it came time to test the antitampering tag, Lee ran into a problem: It was very difficult and time-consuming to take precise enough measurements to determine whether two glue patterns matched.
He reached out to a friend in the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL), and together, they tackled the problem using AI.
They trained a machine-learning model to compare glue patterns and calculate their similarity with more than 99% accuracy.
"One drawback is that we had a limited data sample for this demonstration, but we could improve the neural network in the future if a large number of these tags were deployed in a supply chain, giving us a lot more data samples," Lee says.
The challenges and opportunities of terahertz waves
The authentication system is also limited because terahertz waves suffer from high loss levels during transmission, so the sensor can only be about 4 centimeters from the tag to get an accurate reading.
This distance wouldn't be an issue for an application like barcode scanning, but it would be too short for some potential uses, such as in an automated highway toll booth. Also, the angle between the sensor and tag must be less than 10 degrees, or the terahertz signal will degrade too much.
They plan to address these limitations in future work and inspire other researchers to be more optimistic about what can be accomplished with terahertz waves despite the many technical challenges, says Han.
"One thing we really want to show here is that the application of the terahertz spectrum can go well beyond broadband wireless. In this case, you can use terahertz for ID, security, and authentication. There are a lot of possibilities out there," he adds.
