Electronic transaction authentication — A survey on multimodal biometrics

Shunmugam, S.; Selvakumar, R.K.

doi:10.1109/iccic.2014.7238509

Cited by 7 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently, deep neural networks have shown good performance against iris spoofing attacks [200,112]. Beyond that, in [172], an iris recognition method based on random projections and sparse representations was proposed by Pillai et al This method gains high accuracy about 99%. At the same time, the method can also protect user privacy but the level is only medium.…”

Section: Replay Attack Defensementioning

confidence: 99%

Attacks and defenses in user authentication systems: A survey

Wang

Yan

Zhang

et al. 2021

Journal of Network and Computer Applications

View full text Add to dashboard Cite

Section: Replay Attack Defensementioning

confidence: 99%

Attacks and defenses in user authentication systems: A survey

Wang

Yan

Zhang

et al. 2021

Journal of Network and Computer Applications

View full text Add to dashboard Cite

“…Kannavara and Bourbakis [1] summarized a series of biometric recognition methods based on neural networks by using voice, iris, fingerprint, palm-print and face and pointed out potential ways to improve these methods. Shunmugam and Selvakumar [2] believed that unimodal biometric methods are limited. Multimodal biometric methods are much more reliable for building up a safer authentication system.…”

Section: Introductionmentioning

confidence: 99%

A Survey on Biometric Authentication: Toward Secure and Privacy-Preserving Identification

2019

View full text Add to dashboard Cite

In order to overcome the difficulty of password management and improve the usability of authentication systems, biometric authentication has been widely studied and has attracted special attention in both academia and industry. Many biometric authentication systems have been researched and developed, especially for mobile devices. However, the existing biometric authentication systems still have defects. Some biological features have not been deeply investigated. The existing systems could be vulnerable to attacks, such as replay attack and suffer from user privacy intrusion, which seriously hinder their wide acceptance by end users. The literature still lacks a thorough review on the recent advances of biometric authentication for the purpose of secure and privacy-preserving identification. In this paper, we classify and thoroughly review the existing biometric authentication systems by focusing on the security and privacy solutions. We analyze the threats of biometric authentication and propose a number of criteria with regard to secure and privacy-preserving authentication. We further review the existing works of biometric authentication by analyzing their differences and summarizing the advantages and disadvantages of each based on the proposed criteria. In particular, we discuss the problems of aliveness detection and privacy protection in biometric authentication. Based on our survey, we figure out a number of open research issues and further specify a number of significant research directions that are worth special efforts in future research.

show abstract

“…Hence, even though efficiency as a metric for performance may be considered the most important characteristic in most cases, a high-performance system will have reduced utility in a security application if the modality can be easily forged or if it lacks universality. Unfortunately, sources such as [10], [11] and [12] fail to provide a quantitative method for attributes' evaluation other than performance. To overcome the limitations inherent to single modality systems and in order to take advantage of different modalities' strengths, the use of multimodal biometric systems has been proposed and tested as a reliable alternative [13].…”

Section: Introductionmentioning

confidence: 99%

BIOMEX-DB: A Cognitive Audiovisual Dataset for Unimodal and Multimodal Biometric Systems

et al. 2021

View full text Add to dashboard Cite

Multimodal biometric schemes arise as an interesting solution to the multidimensional reinforcement problem for biometric security systems. Along with the performance dimension, these systems should also comply with required levels for other conditions such as permanence, collectability, and circumvention, among others. In response to the demand for a multimodal and synchronous dataset, in this paper we introduce an open access database of synchronously recorded electroencephalogram signals (EEG), voice signals and video feed from 51 volunteers, 25 female, 26 male, captured for (but not limited to) biometric purposes. A total of 140 samples were collected from each user when pronouncing single digits in Spanish, giving a total of 7140 instances. EEG signals were captured using a 14-channel Emotiv ™ Epoc headset. The resulting set becomes a valuable resource when working on unimodal biometric systems, but significantly more for the evaluation of multimodal variants. Furthermore, the usefulness of the collected signals extends to being exploited by projects in brain computer interfaces and face recognition to name just a few. As an initial report on data separability of the related samples, six user recognition experiments are presented: a face recognition identifier with accuracy of 99%, two speaker identification systems with maximum accuracy of 100%, a bimodal face-speech verification case with Equal Error Rate around 2.64, an EEG identification example, and a bimodal user identification exercise based on EEG and voice modalities with a registered accuracy of 97.6%.

show abstract

Electronic transaction authentication — A survey on multimodal biometrics

Cited by 7 publications

References 9 publications

Attacks and defenses in user authentication systems: A survey

Attacks and defenses in user authentication systems: A survey

A Survey on Biometric Authentication: Toward Secure and Privacy-Preserving Identification

BIOMEX-DB: A Cognitive Audiovisual Dataset for Unimodal and Multimodal Biometric Systems

Contact Info

Product

Resources

About