• INCHARA K M
• Meghana Kulkarni
• Prashant Dhope

The growing reliance on IoT demands secure, lightweight, and tamper-resistant authentication mechanisms. This work implements a Ring Oscillator Physically Unclonable Function (RO-PUF) on a Nexys A7 FPGA to generate unique challenge–response pairs (CRPs) without storing keys in memory. A 128-bit secret key was derived and tested for uniqueness, reliability, and entropy. Machine learning attacks, including Logistic Regression, SVM, and DNN, achieved near-random accuracy, proving resilience. The design offers a low-cost, scalable solution for IoT authentication and cryptographic key generation.

RO-PUF, FPGA, IoT security, authentication, cryptographic key, machine learning resistance,Ring Oscillator

"TRUSTPUF - A Resilient FPGA RO-PUF for Secure Authentication", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 9, page no.c751-c759, September-2025, Available :http://www.jetir.org/papers/JETIR2509287.pdf

"TRUSTPUF - A Resilient FPGA RO-PUF for Secure Authentication", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 9, page no. ppc751-c759, September-2025, Available at : http://www.jetir.org/papers/JETIR2509287.pdf