A Robust Framework for Deep Learning Approaches to Facial Emotion Recognition and Evaluation

Siddiqui, Nyle; Dave, Rushit; Bauer, Theodore J.; Reither, Thomas; Black, Dylan S.; Mitchell, Hanson,

doi:10.48550/arxiv.2201.12705

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As threatening to biometric-based validation, PLA utilizes substantially traits of an obtained sign to verify a purchaser with the exception of the need for a truckload extra hardware. With wired and wi-fi organizations' quickly creating importance because of the extended utilization of the Internet of Things (IoT) gadgets, as appropriately as the ongoing advancements in 5G organizations, the wellbeing of these organizations are vital in ensuring their broad execution and reliability [22][23][24][25]. A regular occurrence of the utilization of substantial layer validation in a Multiple Input Multiple Output (MIMO) net-work is the Bob, Alice, and Eve model.…”

Section: Authentication Schemes Using Machine Learningmentioning

confidence: 99%

Machine learning Applications of Data Security and Privacy A Systemic Review

Dave¹

2022

Preprint

Self Cite

View full text Add to dashboard Cite

<p><em>With the present day trends in technology, greater and more human beings rely on their non-public devices to preserve their sensitive information. Concurrently, the environment in which these devices are linked have grown to develop to be higher dynamic and complex. This opens the communicate of if the modern authentication techniques being used in these devices are reliable adequate to hold these user’s files safe. This paper examines the wonderful purchaser authentication schemes proposed to make larger the safety of great devices. This article is wreck up into two one of a variety avenues discussing authentication schemes that use each be- havioral biometrics or bodily layer authentication. This survey will discuss about every the advantages and challenges that show up with the accuracy, usability, and widespread safety of computing machine getting to recognize techniques in these authentication systems. This article pursuits to beautify in addition look up in this challenge by means of exhibiting the extra than a few existing day authentication models, their schematics, and their results.</em></p>

show abstract

Section: Authentication Schemes Using Machine Learningmentioning

confidence: 99%

Machine learning Applications of Data Security and Privacy A Systemic Review

Dave¹

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, despite having all of this personal data on devices, the current security measures taken to protect this data are weak. The use of a one-time password or physiological biometric much like the scanning of a fingerprint which has become common in the past years are not as strong as they appear (Alqarni et al, 2020, Siddiqui et al, 2022, Shelton et al, 2018. While both of these authentication methods can be extremely convenient for a user, the convenience of logging into a device does not outweigh the high threat of an attack that these methods carry with them.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of a User Authentication Schema Using Behavioral Biometrics and Machine Learning

Pryor¹,

Mallet²,

Dave³

et al. 2022

CIS

Self Cite

View full text Add to dashboard Cite

The amount of secure data being stored on mobile devices has grown immensely in recent years. However, the security measures protecting this data have stayed static, with few improvements being done to the vulnerabilities of current authentication methods such as physiological biometrics or passwords. Instead of these methods, behavioral biometrics has recently been researched as a solution to these vulnerable authentication methods. In this study, we aim to contribute to the research being done on behavioral biometrics by creating and evaluating a user authentication scheme using behavioral biometrics. The behavioral biometrics used in this study include touch dynamics and phone movement, and we evaluate the performance of different single-modal and multi-modal combinations of the two biometrics. Using two publicly available datasets - BioIdent and Hand Movement Orientation and Grasp (H-MOG), this study uses seven common machine learning algorithms to evaluate performance. The algorithms used in the evaluation include Random Forest, Support Vector Machine, K-Nearest Neighbor, Naive Bayes, Logistic Regression, Multilayer Perceptron, and Long Short-Term Memory Recurrent Neural Networks, with accuracy rates reaching as high as 86%.

show abstract

A Robust Framework for Deep Learning Approaches to Facial Emotion Recognition and Evaluation

Cited by 2 publications

References 0 publications

Machine learning Applications of Data Security and Privacy A Systemic Review

Machine learning Applications of Data Security and Privacy A Systemic Review

Evaluation of a User Authentication Schema Using Behavioral Biometrics and Machine Learning

Contact Info

Product

Resources

About