att_abstract={{Smartphones and tablets are excellent point-and-shoot cameras, with users taking dozens of pictures and videos any time and everywhere. Wearables like smart goggles can record media in even more subtle ways in public and private places, with little or no awareness from the subjects in the surroundings. The pervasive use of these devices can compromise the privacy of all the individuals that are unaware subjects of these many pictures and videos, which could also be published without explicit consent on the Internet and social media. This paper proposes Do Not Capture (DNC), a novel technology that removes unwilling subjects from media that includes them at capture time. Through a combination of mutual cooperation between mobile devices and complex— yet resource efficient—vision algorithms, DNC can effectively obfuscate unwilling subjects in pictures with high ac- curacy. DNC is completely distributed, with no need of cloud support, and is designed to efficiently run on a mo- bile device in a scalable manner with little impact on its performance, namely battery and computation. DNC is implemented on a number of Android smartphones and validated through an extensive experimental investigation involving a number of subjects in different indoor and outdoor contexts.}},
	att_authors={mr047v, ez2685},
	att_categories={C_NSS.7, C_NSS.13},
	att_copyright_notice={{This version of the work is reprinted here with permission of IEEE for your personal use. Not for redistribution. The definitive version was published in IEEE Internet Computing . {{, 2017-04-20}}
	att_tags={Mobile Sensing,  Privay,  Wearables,  Smart Mobile Devices},
	author={Moo-ryong Ra and Eric Zavesky and Seungjoon Lee and Emiliano Miluzzo},
	institution={{IEEE Internet Computing }},
	title={{Do Not Capture: Automated Obscurity for Pervasive Imaging}},