Trustworthiness and truthfulness issues in big crowd-sensed dataSpeaker: Burak Kantarci – Ottawa, ON, Canada
Topic(s): Networks and Communications
AbstractAs a cloud-inspired sensing service model, mobile crowd-sensing can enable access to the Internet of Things (IoT)-based services. When mobile crowd-sensing becomes widely adopted, sensed data from mobile devices can be accessed by IoT applications on a pay-as-you-go fashion. In the presence of adversaries aiming at misinformation through manipulation of their sensing data, trustworthiness of big crowd-sensed data introduces a crucial concern for the end users of crowd-sensing-based services. This lecture provides an overview of the state of the art in mobile crowd-sensing, and presents recent research that addresses the trustworthiness challenges in crowd-sensed big data acquisition. Outlier detection-backed statistical reputation models, social network Sybil detection-inspired recommendation models, and hybrid models are presented with pros and cons. In addition, an anchor-assisted recommendation in data acquisition is introduced along with a thorough discussion on its benefits and overheads. I also report open issues, existing challenges and possible research directions in this field.
About this LectureNumber of Slides: 35
Duration: 60 minutes
Languages Available: English
Request this Lecture
To request this particular lecture, please complete this online form.
Request a Tour
To request a tour with this speaker, please complete this online form.
All requests will be sent to ACM headquarters for review.