Privacy protection framework for face recognition in edge-based Internet of Things

Xie, Yun; Nedjah, Nadia; Gupta, Brij B.; Taniar, David; Zhang, Jindan

doi:10.1007/s10586-022-03808-8

Cited by 10 publications

(2 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other studies use local differential privacy to ensure that individual data points cannot be reverse-engineered or identified. The work of [33] proposes a general privacy protection framework for edge-based face recognition systems. This is done through a local differential privacy algorithm based on the proportion difference of feature information.…”

Section: A Privacy-preserving Face Recognitionmentioning

confidence: 99%

Maintaining Privacy in Face Recognition Using Federated Learning Method

Woubie,

Solomon,

Attieh

2024

IEEE Access

View full text Add to dashboard Cite

The state-of-the-art face recognition systems are typically trained on a single computer, utilizing extensive image datasets collected from various users. Nevertheless, these datasets often contain sensitive personal information that users may hesitate to disclose. To address potential privacy concerns, we explore the application of federated learning, both with and without secure aggregators, in the context of both supervised and unsupervised face recognition systems. Federated learning facilitates the training of a shared model without necessitating the sharing of individual private data, achieving this by training models on decentralized edge devices housing the data. In our proposed system, each edge device independently trains its own model, which is subsequently transmitted either to a secure aggregator or directly to the central server. To introduce diverse data without the need for data transmission, we employ generative adversarial networks to generate imposter data at the edge. Following this, the secure aggregator or central server combines these individual models to construct a global model, which is then relayed back to the edge devices. Experimental findings based on the CelebA datasets reveal that employing federated learning in both supervised and unsupervised face recognition systems offers dual benefits. Firstly, it safeguards privacy since the original data remains on the edge devices. Secondly, the experimental results demonstrate that the aggregated model yields nearly identical performance compared to the individual models, particularly when the federated model does not utilize a secure aggregator. Hence, our results shed light on the practical challenges associated with privacy-preserving face image training, particularly in terms of the balance between privacy and accuracy.

show abstract

Section: A Privacy-preserving Face Recognitionmentioning

confidence: 99%

Maintaining Privacy in Face Recognition Using Federated Learning Method

Woubie,

Solomon,

Attieh

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Et. Al in [82] works on the security and privacy of face recognition systems by making the system secure against man-in- middle attacks and temper attacks. J. Galbally et al in [79] show that the Bayesian hill-climbing attack is effective and faster than the brute force attack for all operating points.…”

Section: Authentication Based On Face Scanmentioning

confidence: 99%

Performance Analysis of Authentication system: A Systematic Literature Review

Singla

Verma

2023

Preprint

View full text Add to dashboard Cite

Data authentication is vital nowadays, as the development of the internet and its applications allow users to have all-time data availability, attracting attention towards security and privacy and leading to authenticating legitimate users. We have diversified means to gain access to our accounts, like passwords, biometrics, and smartcards, even by merging two or more techniques or various factors of authentication. This paper presents a systematic literature review of papers published from 2010 to 2022 and gives an overview of all the authentication techniques available in the market. Our study provides a comprehensive overview of all three authentication techniques with all the performance metrics (Accuracy, Equal Error Rate (EER), False Acceptance Rate (FAR)), security, privacy, memory requirements, and usability (Acceptability by user)) that will help one choose a perfect authentication technique for an application. In addition, the study also explores the performance of multimodal and multi-factor authentication and the application areas of authentication.

show abstract

Hybrid approach for suspicious object surveillance using video clips and UAV images in cloud-IoT-based computing environment

Ahamad

Mishra

2023

Cluster Comput

View full text Add to dashboard Cite

Privacy protection framework for face recognition in edge-based Internet of Things

Cited by 10 publications

References 37 publications

Maintaining Privacy in Face Recognition Using Federated Learning Method

Maintaining Privacy in Face Recognition Using Federated Learning Method

Performance Analysis of Authentication system: A Systematic Literature Review

Hybrid approach for suspicious object surveillance using video clips and UAV images in cloud-IoT-based computing environment

Contact Info

Product

Resources

About