Litcius/Paper detail

Secured Convolutional Layer IP Core in Convolutional Neural Network Using Facial Biometric

Anirban Sengupta, Rahul Chaurasia

2022IEEE Transactions on Consumer Electronics22 citationsDOI

Abstract

This paper presents a novel methodology to design a secured custom reusable intellectual property (IP) core for the convolutional layer of convolutional neural network (CNN). Since the reusable IP cores used in system-on-chips (SoCs) of consumer electronics (CE) systems are susceptible to the hardware threat of IP counterfeiting. Therefore, this paper also presents the security of the proposed convolutional layer reusable IP core against the threat of IP counterfeiting using facial biometrics. This enables the integration of secured reusable IP cores in the SoCs of CE systems, thereby ensuring the safety of end consumers. In the proposed approach, the convolutional layer IP core is designed through high-level synthesis (HLS) process and secured by embedding secret biometric security information into the design during register allocation phase of the HLS process. The qualitative and quantitative analysis of the proposed approach exhibits significantly lower probability of coincidence (Pc) (up to 47% less) and higher tamper tolerance (1.93E+25) than recent approaches. Further, it offers robust security with zero design overhead.

Topics & Concepts

Convolutional neural networkComputer scienceEmbedded systemOverhead (engineering)BiometricsProcess (computing)Computer networkLayer (electronics)Computer hardwareComputer securityArtificial intelligenceOperating systemOrganic chemistryChemistryPhysical Unclonable Functions (PUFs) and Hardware SecurityNeuroscience and Neural EngineeringCell Image Analysis Techniques
Secured Convolutional Layer IP Core in Convolutional Neural Network Using Facial Biometric | Litcius