Secure PUF-based Authentication and Key Exchange Protocol using Machine Learning

Amir Ali Pour (1, 2, 3) , Fatemeh Afghah (2) , David Hely (4) , Vincent Beroulle (3) , Giorgio Di Natale (1)

1 TIMA-AMfoRS - Architectures and Methods for Resilient Systems
2 Clemson University
3 LCIS - Laboratoire de Conception et d'Intégration des Systèmes
4 CEA-LETI - Commissariat à l'énergie atomique et aux énergies alternatives - Laboratoire d'Electronique et de Technologie de l'Information

Error Correction Codes and Fuzzy Extractors (FE) using publicly available helper data are used to increase the reliability of the secret value generated from noisy sources such as Physically Unclonable Functions (PUFs). Publicly available helper data is, in turn, vulnerable against Helper Data ma- nipulation attacks due to its correlation with the secret value. Instead of using helper data for FE-based error correction, we propose a locally recoverable repetition coding mechanism. Our proposed mechanism is based on sharing only the user’s generated challenge values, which is inherently secure against machine learning and PUF cloning attacks. We evaluate the reliability of our method using simulated challenge response pairs (CRP)s captured from various XOR Arbiter PUF structures at different levels of noise embedded in the PUF CRP characteristic. We show for instance that in a scenario of using PUF with 10% error-rate, our method can successfully recover the encryption key with close to zero failure-rate with a repetition code length of 10 or higher.

Domaines: Micro et nanotechnologies/Microélectronique

Amir Ali Pour, Fatemeh Afghah, David Hely, Vincent Beroulle, Giorgio Di Natale. Secure PUF-based Authentication and Key Exchange Protocol using Machine Learning. IEEE Computer Society Annual Symposium on VLSI (ISVLSI 2022), Jul 2022, Pafos, Cyprus. ⟨hal-03689856⟩