Securing Deep Learning Based Edge Finger Vein Biometrics With Binary Decision Diagram

Yang, Wencheng; Wang, Song; Hu, Jiankun; Zheng, Guanglou; Yang, Jucheng; Valli, Craig

doi:10.1109/tii.2019.2900665

Cited by 49 publications

(25 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although cloud servers own super-powerful service ends and have a fast data processing speed, data transportation has become a bottleneck. Also, unnecessary bandwidth costs are high if tremendous volumes of raw data are exchanged between end users and the cloud server [1]. Authentication is the act of confirming the truth of an attribute of a datum or entity.…”

mentioning

confidence: 99%

“…There are many applications of edge biometrics with AI. We give three examples in [1]. 1) Automated surveillance: Smart cameras with built-in AI capabilities can figure out whom they are see inland track specific individuals; 2) Gait identification: By using specific sensors on a mobile device, a person's way of walking can be identified by AI algorithms.…”

mentioning

confidence: 99%

“…The transformed version is further processed by a multilayer extreme learning machine (ML-ELM) for training and classification. Thanks to template protection, the deep learning based privacy preserving finger vein recognition system named BDD-ML-ELM has heightened security [1].…”

mentioning

confidence: 99%

“…In [1,3], Miura et al proposed to use repeated line tracking to extract finger-vein features from an unclear finger-vein image. The line tracking operation starts from different positions and is repeated multiple times.…”

mentioning

confidence: 99%

“…As we are going work on deep learning based approach, our main focus or aim to AI, machine learning or deep learning and it has achieved promising results in tasks, such as speech, image, and video processing, as well as, biometric recognition, e.g., finger vein image recognition. In [1], they proposed an algorithm which is capable of creating a new noninvertible version of the original finger-vein template, which is stacked with an artificial neural network-the multilayer extreme learning machine (ML-ELM) to generate a privacy-preserving finger-vein recognition system i.e. named BDD-ML-ELM.…”

mentioning

confidence: 99%

See 4 more Smart Citations

A Hybrid Approach for Deep Learning Based Finger Vein Biometrics Template Security

Shendre¹,

Sapkal²

2020

IZVESTIYA SFedU. ENGINEERING SCIENCES

View full text Add to dashboard Cite

Мы живем в современном обществе, где у нас достаточно много ресурсов и вычислительной мощности, единственной проблемой остается общественная безопасность. С развитием технологий личная информация становится все более не защищенной. Поэтому идентификация личности является актуальной проблемой. Существующие традиционные методы защиты личной информации оказались не надежными. Защита биометрических параметров является одной из наиболее важных проблем при обеспечении безопасности современной биометрической системы. Имеющиеся алгоритмы не дают адекватного решения этой проблемы. Поэтому мы попытались предложить метод, который будет более актуальным. В этой статье обсуждается гибридный метод биометрического распознавания вен на пальцах, основанный на методе глубокого обучения с использованием схем двоичной диаграммы принятия решений и нечетких обязательств. Предложенный гибридный метод состоит из четырех частей, а именно: извлечение признаков вены пальца, генерация защищенного шаблона, схема нечеткой фиксации, распознавание и принятие решения о структуре вен на пальце. Таким образом, имеются четыре модуля, при этом каждый модуль работает эффективно и дает точные результаты по всем базам данных. Биометрия, безопасность шаблонов, гибрид, двоичная диаграмма принятия решений (BDD), схема нечетких обязательств, глубокое обучение и машинное обучение. Shivam Shendre, Dr. Shubhangi Sapkal A HYBRID APPROACH FOR DEEP LEARNING BASED FINGER VEIN BIOMETRICS TEMPLATE SECURITY We are living in the today's society, where we have fairly-enough storage capacity and processing power, the only issue is with security. As, the technologies are evolving with faster rate, we are tend to grow the use of electronic devices rapidly in todays' society, it started to flow or leakage of personal information around/across, which then leads to breach of this information. Now, personal or identical verification is key problem is being crucial. So whatever traditional methods we have for providing authentication or security those have proven inadequate to be unreliable and do not provide strong security. Biometric template protection is one of the most important issues in securing today's biometric system. We have many algorithms which don't give adequate solution for the same. So we tried to give a method which will reach to the expectations more satisfactorily and certainly to the extent required. In this paper we have discussed a hybrid method for finger vein biometric recognition based on deep learning approach using BDD and fuzzy commitment schemes. The proposed hybrid method consists of four parts, namely Finger vein feature extraction, BDD-based secure template generation, Fuzzy commitment scheme and ML based finger vein recognition and decision making. Thus it has four module and each module works efficiently and gives accurate results on all databases. Biometric, template security, hybrid, binary decision diagram (BDD), fuzzy commitment scheme, deep learning and machine learning Introduction. Biometric recognition is a reliable, robust, and conv...

show abstract

mentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

A Hybrid Approach for Deep Learning Based Finger Vein Biometrics Template Security

Shendre¹,

Sapkal²

2020

IZVESTIYA SFedU. ENGINEERING SCIENCES

View full text Add to dashboard Cite

show abstract

Template Protection Based on Chaotic Map for Finger Vein Recognition

Shao

Ren

Sun

et al. 2021

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

While the widespread application of biometric identification technology has provided convenient services, the security, and privacy of personal data have also attracted increasing attention. Because biometric traits are unique, once an attack occurs, the information stored in the system will be permanently leaked. Thus, ensuring the security of biometric templates is a major challenge. In order to solve this problem, we propose a finger vein template protection method based on chaotic map. First, we randomize and scramble the finger vein features after feature extraction, disturbing the location distribution of the pixels. Second, on the basis of the chaotic features of the finger veins, binary quantization is applied to further ensure the safety of the template. Finally, the compact and safe finger vein template is directly stored in the database. Finger vein matching is realized in the encryption domain, which changes the way that the traditional finger vein recognition system directly stores biometric templates. We conducted a series of detailed experiments on the public dataset. The experimental results show that our method can ensure the safety of finger vein templates while maintaining stable recognition performance. Moreover, the method has universality for different feature-extraction methods and meets the requirements of good biometric template protection.

show abstract

Evolution toward intelligent communications: Impact of deep learning applications on the future of 6G technology

Abd Elaziz,

Al‐qaness,

Dahou

et al. 2023

WIREs Data Min & Knowl

View full text Add to dashboard Cite

The sixth generation (6G) represents the next evolution in wireless communication technology and is currently under research and development. It is expected to deliver faster speeds, reduced latency, and greater capacity compared to the current 5G wireless technology. 6G is envisioned as a technology capable of establishing a fully data‐driven network, proficient in analyzing and optimizing end‐to‐end behavior and handling massive volumes of real‐time data at rates of up to terabits per second (Tb/s). Moreover, 6G is designed to accommodate an average of 1000+ substantial connections per person over the course of a decade. The concept of a data‐driven network introduces a new service paradigm, which offers fresh opportunities for applications within 6G wireless communication and network design in the future. This paper aims to provide a survey of existing applications of 6G that are based on deep learning techniques. It also explores the potential, essential technologies, scenarios, challenges, and related topics associated with 6G. These aspects are crucial for meeting the requirements for the development of future intelligent networks. Furthermore, this work delves into various research gaps between deep learning and 6G that remain unexplored. Different potential deep learning applications for 6G networks, including privacy, security, environmentally friendly communication, sustainability, and various wireless applications, are discussed. Additionally, we shed light on the challenges and future trends in this field.This article is categorized under: Technologies > Computational Intelligence Fundamental Concepts of Data and Knowledge > Explainable AI Technologies > Machine Learning

show abstract

Securing Deep Learning Based Edge Finger Vein Biometrics With Binary Decision Diagram

Cited by 49 publications

References 30 publications

A Hybrid Approach for Deep Learning Based Finger Vein Biometrics Template Security

A Hybrid Approach for Deep Learning Based Finger Vein Biometrics Template Security

Template Protection Based on Chaotic Map for Finger Vein Recognition

Evolution toward intelligent communications: Impact of deep learning applications on the future of 6G technology

Contact Info

Product

Resources

About