Implicit IoT authentication using on-phone ANN models and breathing data

Vhaduri, Sudip; Dibbo, Sayanton V.; Cheung, William

doi:10.1016/j.iot.2023.101003

Cited by 6 publications

(1 citation statement)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The work [ 22 ] used continuous microphone monitoring to verify breathing patterns for implicit IoT authentication. BTL Auth, an on-phone authentication software powered by Tensor Flow Lite and driven by breathing data, uses a neural network model to validate the target user and an audio processing pipeline to filter and compute features.…”

Section: Related Workmentioning

confidence: 99%

Two-Layered Multi-Factor Authentication Using Decentralized Blockchain in an IoT Environment

Bamashmos,

Chilamkurti,

Shahraki

2024

Sensors

View full text Add to dashboard Cite

Internet of Things (IoT) technology is evolving over the peak of smart infrastructure with the participation of IoT devices in a wide range of applications. Traditional IoT authentication methods are vulnerable to threats due to wireless data transmission. However, IoT devices are resource- and energy-constrained, so building lightweight security that provides stronger authentication is essential. This paper proposes a novel, two-layered multi-factor authentication (2L-MFA) framework using blockchain to enhance IoT devices and user security. The first level of authentication is for IoT devices, one that considers secret keys, geographical location, and physically unclonable function (PUF). Proof-of-authentication (PoAh) and elliptic curve Diffie–Hellman are followed for lightweight and low latency support. Second-level authentication for IoT users, which are sub-categorized into four levels, each defined by specific factors such as identity, password, and biometrics. The first level involves a matrix-based password; the second level utilizes the elliptic curve digital signature algorithm (ECDSA); and levels 3 and 4 are secured with iris and finger vein, providing comprehensive and robust authentication. We deployed fuzzy logic to validate the authentication and make the system more robust. The 2L-MFA model significantly improves performance, reducing registration, login, and authentication times by up to 25%, 50%, and 25%, respectively, facilitating quicker cloud access post-authentication and enhancing overall efficiency.

show abstract

Section: Related Workmentioning

confidence: 99%