Date of Graduation


Document Type


Degree Name

Doctor of Philosophy in Computer Science (PhD)

Degree Level



Computer Science & Computer Engineering


Qinghua Li

Committee Member

Xintao Wu

Second Committee Member

Susan Gauch

Third Committee Member

Jingxian Wu


Mobile Phone, Photo, Privacy


Today, we are living in environments that are full of cameras embedded in devices such as smart phones and wearables. These mobile devices and as well as apps installed on them are designed to be extremely convenient for users to take, store and share photos. In spite of the convenience brought by ubiquitous cameras, users' privacy may be breached through photos that are taken and stored with mobile devices. For example, when users take a photo of a scenery, a building or a target person, a stranger may also be unintentionally captured in the photo. Such photos expose the location and activity of strangers, and hence may breach their privacy. In addition, photos that are stored on smartphones may contain private information (e.g., driver's license) about phone owners, which raise people’s privacy concerns over unauthorized access by installed apps.

The goal of this dissertation is to protect people's privacy in photo taking and accessing. To achieve this goal, we propose several systems to address the aforementioned privacy issues.

To protect stranger's privacy in photo taking, we proposed two systems called PrivacyCamera and PoliteCamera. Through cooperation between the photographer and the stranger, these systems can automatically blur the stranger’s face in the photo upon the stranger’s request when the photo is being taken. Even though PrivacyCamera and PoliteCamera can successfully protect stranger's privacy, they depend on the cooperation between the photographer and the stranger. That requires both the photographer and stranger to install the proposed systems on their mobile phones; however, this is not always possible. Therefore, we further propose a feature-based model to automatically distinguish the target from strangers in a photo, so that we can blur all strangers' faces without the cooperation. Finally, we designed PhotoSafer, a content-based and context-aware to protect private photos from unauthorized access on Android phones.

In future work, we plan to design a privacy-preserving online sharing system, which has less burden of policy settings and can protect the privacy of strangers in a photo. In addition, we will also consider designing personalized systems to protect user-specific private photos.