Authors: Jasmine DeHart, Christan Grant. Sunbelt Conference, International Network for Social Network Analysis (INSNA) XLII. Cairns, Australia. July 2022. [poster]
Large-scale networks are complex and can be difficult to dissect insights or meaning from. Researchers have described networks with the use of grammars and centrality measurements. Given the massive amounts of possible grammars, researchers cannot use grammars to describe networks. The interpretation of a centrality measurement can be vague and lead to unexplainable findings in complex networks. A promising direction to understand complex networks is with the use of mechanisms.Back to top of page
Authors: Jasmine DeHart, Oluwasijibomi Ajisegiri, Greg Erhardt, Jamie Cleveland, Corey E. Baker, Christan Grant. International Journal on Advances in Intelligent Systems, Vol. 14, No. 1. December 2021. [PDF]
The term "smart city" is widely used, but there is no consensus on the definition. Many citizens and stakeholders are unsure about what a smart city means in their community and how it affects cost and privacy. This paper describes how city planners and companies envision a smart city using data from the 2015 Smart City Challenge. We use text analysis techniques to investigate the technology and themes necessary for creating a smart city using surveys, document similarity, cluster analysis, and topic modeling from the seven finalists from the 2015 Smart City Challenge Applicants.
In an ideal world, deployed machine learning models will enhance our society. We hope that those models will provide unbiased and ethical decisions that will benefit everyone. However, this is not always the case; issues arise during the data preparation process throughout the steps leading to the models' deployment. In this work, we walk through the decision making process that a researcher should consider before, during, and after a system deployment to understand the broader impacts of their research in the community. We examine visual privacy research and draw lessons that can apply broadly to artificial intelligence.
Authors: Makya Stell, Jasmine DeHart, Christan Grant.
27th Annual OK-LSAMP Research Symposium. October 2021.
Social Media Networks (SMNs) allow users to post private visual content (images and videos) that exposes sensitive information without warning or attempting to mitigate these risks. Because users post this information using "trendy" hashtags and keywords, distinguishing exact triggers that prompt the need for mitigation has become increasingly difficult. All SMN applications require camera permissions for users to have access to all of the features. This is useful for privacy considerations because the software will only monitor the device's camera activity on applications that have camera permissions.Back to top of page
Authors: Jasmine DeHart, Makya Stell, Christan Grant Information (MDPI). Special Issue: End of Privacy? 11(2), 57. 2020. [PDF]
Online privacy has become immensely important with the growth of technology and the expansion of communication. Social Media Networks have risen to the forefront of current communication trends. With the current trends in social media, the question now becomes how can we actively protect ourselves on these platforms? In this study, we investigate (1) the users' perspective of privacy, (2) pervasiveness of privacy leaks on Twitter, and (3) the threats and dangers on these platforms.
The expectation of people and futurists is that all respectable cities will become Smart Cities in the near future. Two main barriers stand in the way of the evolution of cities. First is cost, the transformation into a smart city is expensive (e.g., between $30 Million and $40 Billion) and only a few cities are able to obtain the resources required for upgrades. Second, many citizens equate the data collection and surveillance of smart city technology with aggressive infringements on privacy. In this paper, we describe how citizens, city planners, and companies can develop smart cities that do not require crippling loans and are respectful of privacy.Back to top of page
In recent years machine learning has become a common part of technology and society. With the integration of these models in to applications, it is essential to encompass a plethora of data reflective of the population. However, machine learning models are not easy to tailor for a variety of demographics so issues with bias, fairness, and accountability arise. The primary goal of this study is to understand how biases in computer vision techniques can affect the pervasiveness of social media-based privacy leaks. To mitigate privacy leaks on social media, we propose a computer vision system to identify content and mitigation techniques to reduce exposure of social media network users.Back to top of page
With the growth and accessibility of mobile devices and internet, the ease of posting and sharing content on social media networks (SMNs) has increased exponentially. Many users post images that contain "privacy leaks" regarding themselves or someone else. In this work, we investigate (1) how pervasive social media-based privacy visual content leaks are and (2) what reasonable mitigation strategies can be developed to detect and minimize these leaks.Back to top of page