Integrated Circuit Identification and True Random Numbers using 1.5-Transistor Flash Memory

Lawrence Clark, James Adams, Keith Holbert
Arizona State University


Abstract

Flash memory bits, like other integrated circuit (IC) devices, are prone to random variability in their actual vs. nominal characteristics. We present the use of 1.5-T flash memory cells in physically unclonable functions (PUFs) leveraging their erase speed variability. This type of memory is interesting for the internet of things (IOT) due to its wide availability as IP at foundries. Using experimentally measured results, we show simple methods that provide high reliability with no or limited need for helper data and error correction. High quality fingerprints for IC identification are demonstrated. Moreover, techniques to remove systematic variations from the array response are shown, allowing the resulting binary strings to pass all National Institute of Standards and Technology tests for randomness. Consequently, with low complexity helper functions, true random numbers can be readily produced.