In practice, there are often explicit constraints on what representations or decisions are
acceptable in an application of machine learning. For example it may be a legal requirement …

Wearable computing is rapidly getting deployed in many—commercial, medical, and
personal—domains of day-to-day life. Wearable devices appear in various forms, shapes …

Drones are unmanned aircraft controlled remotely or operated autonomously. While the
extant literature suggests that drones can in principle invade people's privacy, little is known …

Personal data garnered from various sensors are often offloaded by applications to the
cloud for analytics. This leads to a potential risk of disclosing private user information. We …

Users are increasingly vulnerable to inadvertently leaking sensitive information through
cameras. In this paper, we investigate an approach to mitigating the risk of such inadvertent …

Bystanders have little say in whether they are being recorded by" always-on" cameras. One
approach is to use gestural interaction to enable bystanders to signal their preference to …

While media reports about wearable cameras have focused on the privacy concerns of
bystanders, the perspectives of thelifeloggers' themselves have not been adequately …

Eyewear devices, such as augmented reality displays, increasingly integrate eye tracking,
but the first-person camera required to map a user's gaze to the visual scene can pose a …

Low cost digital cameras in smartphones and wearable devices make it easy for people to
automatically capture and share images as a visual lifelog. Having been inspired by a US …

Privacy has become one of the major concerns in cloud video surveillance. Privacy
protection of the surveillance videos strive to protect users' privacy information without …