It is not uncommon for various companies and academics to claim breakthroughs in RFID technology in terms of tag cost, size or other attributes. SCDigest has reported on many of them.
But nearly all of them are hardly heard from again.
Supply Chain Digest Says... |
|
When such a label is removed from an item, it alters the pattern of the metal particles pattern and corresponding terahertz signal, which cannot be duplicated. |
|
What do you say? |
Click here to send us your comments |
|
Click here to see reader feedback |
|
|
|
So we recently have heard of another one from a team of MIT engineers, according to a recent article on the InterestingEngieerig.com web site.
The tags in question are for product authentication, for which RFID technology has supported for years, but with some drawbacks. They RFID tags are relatively large, costly, and vulnerable to counterfeiting.
The MIT team says it has developed a new type of ID tag that overcomes these limitations by using something terahertz waves, which are smaller and faster than the radio waves used with RFID.
The new tag, they say, is based on a chip several times smaller and less expensive then RFID.
The MIT tags also offers improved security, using the unique pattern in the reflection of metal particles added to the glue that attaches the tag to the item as a fingerprint. That means the authentication system will detect tampering if someone tries to peel off the label and stick it to a fake item.
It’s not the first time the researcher have been down this path. Interesting Engineering says that the basic tag was invented a few years ago by the same MIT researchers, but it had a fatal flaw: it had the same security vulnerability as RFID, as the tags could be easily removed and reattached.
The MIT scientists say they have now solved this problem by adding an antitampering feature, which leverages the properties of terahertz waves.
How It Works
Each tag contains tiny slots that allow terahertz waves generated by energizing the tags to pass through and reach the glue layer of a label construction.
(See More Below)
|
CATEGORY SPONSOR: SOFTEON |
|
|
|
|
The researcher added microscopic metal particles to the glue that act as mirrors for terahertz waves, reflecting them back to the tag in a random pattern.
The tag reads the reflected pattern and converts it into a digital code which serves as a fingerprint of each item. The code matched against a database of registered fingerprints to authenticate the item.
That process, the researchers say, was enhanced by development a machine-learning model to identify similar glue patterns with more than 99% accuracy.
When such a label is removed from an item, it alters the pattern of the metal particles pattern and corresponding terahertz signal, which cannot be duplicated. Vendors can take an initial reading of the tag and store the data in the cloud for later authentication.
But there was still a problem.
It was very difficult and time-consuming to take precise enough measurements to determine whether two glue patterns matched.
The answer? What else: AI.
The MIT engineers recruited an MIT colleague and AI expert to help. Together, they trained a machine-learning model to compare glue patterns and calculate their similarity with more than 99% accuracy, Interesting Engineering reports.
There are still some challenges. Right now, the sensor has to be very close to the tag to work, for example. The researchers are optimistic a solution for this can be found.
Any reaction to this new RFID techology? Let us know your thoughts at the Feedback button below.
Your Comments/Feedback
|