Visual Content Privacy Leaks on Social Media Networks

DeHart, Jasmine; Grant, Christan

doi:10.48550/arxiv.1806.08471

Cited by 1 publication

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These types of conflict can affect the privacy of minors [62,63] and bystanders [23,27,57]. This co-owned content can cause privacy leaks without it being the individual's intent [30]. In the ML pipeline, the researcher should consider possible issues for MPC in all phases.…”

Section: Multiparty Conflict (Mpc)mentioning

confidence: 99%

“…To protect the visual privacy of individuals, researchers have suggested the use of concepts like obfuscation [18,29] for mitigating objects and faces and privacy risk scores. The idea of visual privacy mitigation is centered around accessibility and caters to the individualistic concept of privacy [7,30]. Most visual privacy systems use one or more of these five protection techniques [29]: intervention [20], blind vision [20], secure processing [19,20], redaction [18], and data hiding [20].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Proposing an Interactive Audit Pipeline for Visual Privacy Research

DeHart¹,

Xu²,

Egede³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

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. The continued use of biased datasets and biased processes will adversely damage communities and increase the cost to fix the problem later. 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. Throughout this paper, we discuss fairness, privacy, and ownership issues in the machine learning pipeline, assert the need for a responsible human-over -the-loop methodology to bring accountability into machine learning pipeline, and finally, reflect on the need to explore research agendas that have harmful societal impacts. We examine visual privacy research and draw lessons that can apply broadly to artificial intelligence. Our goal is to provide a systematic analysis of the machine learning pipeline for visual privacy and bias issues. With this pipeline, we hope to raise stakeholder (e.g., researchers, modelers, corporations) awareness as these issues propagate in the various machine learning phases.

show abstract