Integrating user feedback is one of the pillars for building successful products. However, this feedback is generally collected in an unstructured free-text form, which is challenging to understand at scale. This is particularly demanding in the privacy domain due to the nuances associated with the concept and the limited existing solutions. In this work, we present Hark1, a system for discovering and summarizing privacy-related feedback at scale. Hark automates the entire process of summarizing privacy feedback, starting from unstructured text and resulting in a hierarchy of high-level privacy themes and fine-grained issues within each theme, along with representative reviews for each issue. At the core of Hark is a set of new deep learning models trained on different tasks, such as privacy feedback classification, privacy issues generation, and high-level theme creation. We illustrate Hark’s efficacy on a corpus of 626 M Google Play reviews. Out of this corpus, our privacy feedback classifier extracts $6 M$ privacy-related reviews (with an AUC-ROC of 0.92). With three annotation studies, we show that Hark’s generated issues are of high accuracy and coverage and that the theme titles are of high quality. We illustrate Hark’s capabilities by presenting high-level insights from $1.3 M$ Android apps.1an English verb meaning to “pay close attention”

Many mobile apps, including augmented-reality games, bar-code readers, and document scanners, digitize information from the physical world by applying computer-vision algorithms to live camera data. However, because camera permissions for existing mobile operating systems are coarse (i.e., an app may access a camera's entire view or none of it), users are vulnerable to visual privacy leaks. An app violates visual privacy if it extracts information from camera data in unexpected ways. For example, a user might be surprised to find that an augmented-reality makeup app extracts text from the camera's view in addition to detecting faces. This paper presents results from the first large-scale study of visual privacy leaks in the wild. We build CamForensics to identify the kind of information that apps extract from camera data. Our extensive user surveys determine what kind of information users expected an app to extract. Finally, our results show that camera apps frequently defy users' expectations based on their descriptions.

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 leaks called privacy markers. Privacy markers give users fine-grained control of what visual information an app can access through a device's camera. We present two examples of this approach: PrivateEye, which allows a user to mark regions of a two-dimensional surface as safe to release to an app, and WaveOff, which does the same for three-dimensional objects. We have integrated both systems with Android's camera subsystem. Experiments with our prototype show that a Nexus 5 smartphone can deliver near realtime frame rates while protecting secret information, and a 26-person user study elicited positive feedback on our prototype's speed and ease-of-use.

Consider the following scenario from the not-too-distant future: the CEO of a company is presenting his vision for the next quarter to a small group of co-workers. The CEO trusts everyone in the room, but many in attendance have smartphones and camera-equipped wearable computing devices running third-party apps. The CEO is worried that this third-party software could leak the highly confidential information in his slides and on the whiteboard. This raises the question: how can the CEO prevent apps with camera access from leaking company secrets?

This paper presents iSee, a crowdsourced approach to detecting and localizing events in outdoor environments. Upon spotting an event, an iSee user only needs to swipe on her smartphone's touchscreen in the direction of the event. These swiping directions are often inaccurate and so are the compass measurements. Moreover, the swipes do not encode any notion of how far the event is located from the user, neither is the GPS location of the user accurate. Furthermore, multiple events may occur simultaneously and users do not explicitly indicate which events they are swiping towards. Nonetheless, as more users start contributing data, we show that our proposed system is able to quickly detect and estimate the locations of the events. We have implemented iSee on Android phones and have experimented in real-world settings by planting virtual "events" in our campus and asking volunteers to swipe on seeing one. Results show that iSee performs appreciably better than established triangulation and clustering-based approaches, in terms of localization accuracy, detection coverage, and robustness to sensor noise.