This Title All WIREs
How to cite this WIREs title:
WIREs Data Mining Knowl Discov
Impact Factor: 7.250

Continuous authentication using biometrics: An advanced review

Full article on Wiley Online Library:   HTML PDF

Can't access this content? Tell your librarian.

Abstract The shortcomings of conventional access control systems for high‐security environments have led to the concert of continuous authentication. Contrary to traditional verification, in which users are authenticated only once at the start of their session, continuous authentication systems regularly check users' identities to prevent hijackings. The challenges in this area involve balancing the security of protected assets by quickly detecting intruders with the system usability for genuine users. Biometric recognition plays a major role within this context, as it is the main way to assure that users are who they claim to be. A comparative analysis of the latest works revealed different aspects of this problem. First, some biometrics traits among those applied for continuous authentication are more suitable for this task than others. Second, systems combining multiple traits have advantages over those relying on a single one. Finally, many works fail to report proper evaluation metrics. With this in mind, we were able to identify new opportunities for researchers in the field. We highlight the potential for mining new datasets on the internet, which would benefit validation and benchmarking, and how recent deep learning techniques could address some of the open challenges in the area. This article is categorized under: Technologies > Prediction Technologies > Machine Learning Application Areas > Science and Technology
Flowchart of different biometric recognition tasks. In enrollment, the template extracted from the input sample is stored together with an identity reference. In verification, the identity reference is used to retrieve a specific template from the gallery, which is then matched against the template extracted from the input sample to decide whether they belong to the same subject or not. In identification, the template extracted from the input sample is matched against all templates in the gallery to retrieve its identity reference. (a) Authentication. (b) Identification
[ Normal View | Magnified View ]
Usual ECG (a), PPG (b), and EEG (c) sensors can be obtrusive or inappropriate in some daily scenarios
[ Normal View | Magnified View ]
Cameras may come built‐in in daily devices at a low cost, such as (a) smartphones and (b) laptops, or be sold separately as a (c) plug‐and‐play peripheral. In most cases, these cameras are capable of capturing color images only, but there are some options nowadays that can capture IR and/or 3D images as well (for a slightly bigger price). For instance, the (c) Intel Realsense SR300 is able to acquire color, IR and 3D images simultaneously and costs around US$100.00. (a) ECG. (b) PPG. (c) EEG
[ Normal View | Magnified View ]
Fingerprint sensors can be embedded in daily devices at a low cost, such as smartphones (a), laptops (b), and mice (c). Although all of them require an undesirable amount of user cooperation, the third is more suitable for continuous authentication because it is a passive acquisition device (Sim et al., ). (a) Smartphone. (b) Laptop. (c) USB multimodal camera
[ Normal View | Magnified View ]
Flowchart of continuous authentication (a) and identification (b) systems. In an authentication system, an initial log‐in operation retrieves or creates the authorized user's template, which is later used to continuously verify the identity of the logged user using recently acquired biometric samples. Whereas in an identification system, user's biometric samples are constantly matched to the entire gallery to retrieve his or her identity and access permissions. (a) Smartphone. (b) Laptop. (c) Mouse
[ Normal View | Magnified View ]

Browse by Topic

Application Areas > Science and Technology
Technologies > Machine Learning
Technologies > Prediction

Access to this WIREs title is by subscription only.

Recommend to Your
Librarian Now!

The latest WIREs articles in your inbox

Sign Up for Article Alerts