The extensive research in the field of multimodal biometrics by the research community and the advent of modern technology has compelled the use of multimodal biometrics in real life applications. Biometric systems that are based on a single modality have many constraints like noise, less universality, intra class variations and spoof attacks. On the other hand, multimodal biometric systems are gaining greater attention because of their high accuracy, increased reliability and enhanced security. This research paper proposes and develops a Convolutional Neural Network (CNN) based model for the feature level fusion of fingerprint and online signature. Two types of feature level fusion schemes for the fingerprint and online signature have been implemented in this paper. The first scheme named early fusion combines the features of fingerprints and online signatures before the fully connected layers, while the second fusion scheme named late fusion combines the features after fully connected layers. To train and test the proposed model, a new multimodal dataset consisting of 1400 samples of fingerprints and 1400 samples of online signatures from 280 subjects was collected. To train the proposed model more effectively, the size of the training data was further increased using augmentation techniques. The experimental results show an accuracy of 99.10% achieved with early feature fusion scheme, while 98.35% was achieved with late feature fusion scheme.
Secure Device Association (also known as security initialization, first-connect or simply pairing in the literature) can be referred as the process of establishing a secure channel between a pair of devices in close proximity. There have been many recent proposals to provide secure pairing of devices in close proximity. All vary in their security against different attacks, the needed hardware capabilities and the necessary level of user attention. In a world of heterogeneous devices and requirements, we need mechanisms to allow automated selection of the best device association protocols without requiring the user to have an in-depth knowledge of the minutiae of the underlying technologies. Further, these mechanisms should facilitate unobtrusive device identification, matching of pairing techniques to requirements, chains of communication to bridge between devices of different capability and improved security by combining techniques where possible. In this paper, we present research trends and issues in the area of secure device association for ad hoc and ubiquitous computing environments followed by a short survey of the existing methods.
A number of traffic characterization studies have been carried out on wireless LANs, which indicate that the wireless settings pose major challenges, especially for high bandwidth and delay sensitive applications. This paper aims to evaluate a number of Quality of Service (QoS) parameters related to video conferencing over three major WLAN Standards 802.11a, 802.11b and 802.11g. To study the traffic characterization behaviour of these WLAN standards, we have simulated the environment for each of these standards and performed experiments. Results are verified through the delivery of successful H.261 video traffic import in OPNET-14 Network simulator. We found that a trade-off exists between the selected data rate, physical characteristics and the frequency spectrum (number of channels) for every standard. The traffic of video conferencing is characterized over each standard in terms of delay performance, traffic performance and load and throughput performance. The results show that quality of video traffic is a function of the frequency band, physical characteristic, maximum data rate and buffer sizes of WLAN standards.
Internet-based cloud technology is a network of remote data centers often placed beyond the country's legal frontiers worldwide. Contrary to the benefits of cloud computing, it is also a target of cybercriminals who may affect its resources on a larger scale by a single exploit. For protecting the cloud resources and increasing the confidence of cloud users, it is necessary to make one accountable for disrupting its services based on relevant evidence that proves someone's guilt in a court of law. In the literature, various frameworks have been presented for evidence collection against the attack on the cloud service for Cloud Service providers (CSP), but there is no framework for LEAs. Unfortunately, the evidence of a security breach in the cloud resides under the control of CSP, which is the sole custodian of cloud resources. However, the CSP does not fully cooperate with the investigators due to various legal, technical, and operational reasons. Hence the entire prosecution is dependent on the provision of evidence by the CSP, which is a great challenge for law enforcement around the world. The study's objective is to design a framework that mitigates the dependency of CSP by collecting the evidence of a security incident outside the cloud by colluding the Internet Service Providers (ISPs) and law Enforcement for a particular cloud service. The framework integrates the components that can detect the attack on a cloud service earlier at ISP and store the logs of the incident in a forensic server which can be used for forensics purposes as and when required.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.