Yining Hu

BreathPrint: Breathing Acoustics-based User Authentication

We propose BreathPrint, a new behavioural biometric signature based on audio features derived from an individuals commonplace breathing gestures. Specifically, BreathPrint uses the audio signatures associated with the three individual gestures: sniff, normal, and deep breathing, which are sufficiently different across individuals. Using these three breathing gestures, we develop the processing pipeline that identifies users via the microphone sensor on smartphones and wearable devices. In BreathPrint, a user performs breathing gestures while holding the device very close to their nose. Using off-the-shelf hardware, we experimentally evaluate the BreathPrint prototype with 10 users, observed over seven days. We show that users can be authenticated reliably with an accuracy of over 94% for all the three breathing gestures in intra-sessions and deep breathing gesture provides the best overall balance between true positives (successful authentication) and false positives (resiliency to directed impersonation and replay attacks). Moreover, we show that this breathing sound based biometric is also robust to some typical changes in both physiological and environmental context, and that it can be applied on multiple smartphone platforms. Early results suggest that breathing based biometrics show promise as either to be used as a secondary authentication modality in a multimodal biometric authentication system or as a user disambiguation technique for some daily lifestyle scenarios.

AFV: enabling application function virtualization and scheduling in wearable networks

Smart wearable devices are widely available today and changing the way mobile applications are being developed. Applications can dynamically leverage the capabilities of wearable devices worn by the user for optimal resource usage and information accuracy, depending on the user/device context and application requirements. However, application developers are not yet taking advantage of these cross-device capabilities. We thus design AFV (Application Function Virtualization), a framework enabling automated dynamic function virtualization/scheduling across devices, simplifying context-aware application development. AFV provides a simple set of APIs hiding complex framework tasks and continuously monitors context/application requirements, to enable the dynamic invocation of functions across devices. We show the feasibility of our design by implementing AFV on Android, and the benefits for the user in terms of resource efficiency and quality of experience with relevant use cases.

Breathing-Based Authentication on Resource-Constrained IoT Devices using Recurrent Neural Networks

Recurrent neural networks (RNNs) have shown promising results in audio and speech-processing applications. The increasing popularity of Internet of Things (IoT) devices makes a strong case for implementing RNN-based inferences for applications such as acoustics-based authentication and voice commands for smart homes. However, the feasibility and performance of these inferences on resource-constrained devices remain largely unexplored. The authors compare traditional machine-learning models with deep-learning RNN models for an end-to-end authentication system based on breathing acoustics.

Are Wearables Ready for HTTPS? On the Potential of Direct Secure Communication on Wearables

The majority of available wearable computing devices require communication with Internet servers for data analysis and storage, and rely on a paired smartphone to enable secure communication. However, many wearables are equipped with WiFi network interfaces, enabling direct communication with the Internet. Secure communication protocols could then run on these wearables themselves, yet it is not clear if they can be efficiently supported.,,,,In this paper, we show that wearables are ready for direct and secure Internet communication by means of experiments with both controlled local web servers and Internet servers. We observe that the overall energy consumption and communication delay can be reduced with direct Internet connection via WiFi from wearables compared to using smartphones as relays via Bluetooth. We also show that the additional HTTPS cost caused by TLS handshake and encryption is closely related to the number of parallel connections, and has the same relative impact on wearables and smartphones.

Are Wearables Ready for Secure and Direct Internet Communication

Recent advances in wearable technology tend towards standalone wearables. Most of todays wearable devices and applications still rely on a paired smartphone for secure Internet communication, even though many current generation wearables are equipped with Wi-Fi and 3G/4G network interfaces that provide direct Internet access. Yet it is not clear if such communication can be efficiently and securely supported through existing protocols. Our findings show that it is possible to use secure and efficient direct communication between wearables and the Internet

AFit: adaptive fitness tracking by application function virtualization

The popularity of wearables is exponentially growing and it is expected that individuals will utilize more than one wearable device at a time in the near future. Efficient resource usage between the devices worn by the same person has not yet been effectively addressed by the current wearable applications. In this paper, we demonstrate the feasibility of application function virtualization by utilizing common capabilities of multiple wearables on the body through a cross-platform Android application - AFit. AFit is developed in a way that it can opportunistically leverage the resources of smartphone, smartwatch and smartglass depending on the context of the user, which is user activity. In this demonstration, AFit shows that it is possible to adaptively select the device to track the user movement for fitness tracking, rather than using randomly selected device or all devices, utilizing the common sensor of accelerometer on all devices.