Brain health attracts more recent attention as the population ages. Smartphone-based gait sensing and analysis can help identify the risks of brain diseases in daily life for prevention. Existing gait analysis approaches mainly hand-craft temporal gait features or developing CNN-based feature extractors, but they are either prone to lose some inconspicuous pathological information or are only dedicated to a single brain disease screening. We discover that the relationship between gait segments can be used as a principle and generic indicator to quantify multiple pathological patterns. In this paper, we propose NeuralGait, a pervasive smartphone-cloud system that passively captures and analyzes principle gait segments relationship for brain health assessment. On the smartphone end, inertial gait data are collected while putting the smartphone in the pants pocket. We then craft local temporal-frequent gait domain features and develop a self-attention-based gait segment relationship encoder. Afterward, the domain features and relation features are fed to a scalable RiskNet in the cloud for brain health assessment. We also design a pathological hot update protocol to efficiently add new brain diseases in the RiskNet. NeuralGait is practical as it provides brain health assessment with no burden in daily life. In the experiment, we recruit 988 healthy people and 417 patients with a single or combination of PD, TBI, and stroke, and evaluate the brain health assessment using a set of specifically designed metrics including global accuracy, exact accuracy, sensitivity, and false alarm rate. We also demonstrate the generalization (e.g., analysis of feature effectiveness and model efficiency) and inclusiveness of NeuralGait.

With the continuing growth of voice-controlled devices, voice metrics have been widely used for user identification. However, voice biometrics is vulnerable to replay attacks and ambient noise. We identify that the fundamental vulnerability in voice biometrics is rooted in its indirect sensing modality (e.g., microphone). In this paper, we present VocalPrint , a resilient mmWave interrogation system which directly captures and analyzes the vocal vibrations for user authentication. Specifically, VocalPrint exploits the unique disturbance of the skin-reflect radio frequency (RF) signals around the near-throat region of the user, caused by the vocal vibrations. The complex ambient noise is isolated from the RF signal using a novel resilience-aware clutter suppression approach for preserving fine-grained vocal biometric properties. Afterward, we extract the vocal tract and vocal source features and input them into an ensemble classifier for authentication. VocalPrint is practical as it allows the effortless transition to a smartphone while having sufficient usability due to its non-contact nature. Our experimental results from 41 participants with different interrogation distances, orientations, and body motions show that VocalPrint achieves over 96 percent authentication accuracy even under unfavorable conditions. We demonstrate the resilience of our system against complex noise interference and spoof attacks of various threat levels.

In this work, we propose a new palm vessel biometric sensing system based on photoacoustic imaging (PAI), which is an emerging technique that allows high-resolution visualization of optical absorption in deep tissue. Our system consists of an ultrasound linear transducer array, an ultrasound data acquisition system, and an Nd:YAG laser emitting 1064 nm wavelength. By scanning the array, we could get a three-dimensional (3D) image of palm vasculature. The 3D image is further combined with our newly developed algorithm, Earth Mover’s Distance - Radiographic Testing (EMD-RT), to provide precise matching and robust recognition rate. Compared to conventional vein sensing techniques, our system demonstrates deeper imaging depth and better spatial resolution, offering securer biometric features to fight against counterfeits. In this study, we imaged twenty different hands at various poses and quantified our system performance. We found that the usability and accuracy of our system are comparable to conventional biometric techniques, such as fingerprint imaging and face identification. Our technique can open up avenues for better liveness detection and biometric measurements.

In autonomous driving, millimeter wave (mmWave) radar has been widely adopted for object detection because of its robustness and reliability under various weather and lighting conditions. For radar object detection, deep neural networks (DNNs) are becoming increasingly important because they are more robust and accurate, and can provide rich semantic information about the detected objects, which is critical for autonomous vehicles (AVs) to make decisions. However, recent studies have shown that DNNs are vulnerable to adversarial attacks. Despite the rapid development of DNN-based radar object detection models, there have been no studies on their vulnerability to adversarial attacks. Although some spoofing attack methods are proposed to attack the radar sensor by actively transmitting specific signals using some special devices, these attacks require sub-nanosecond-level synchronization between the devices and the radar and are very costly, which limits their practicability in real world. In addition, these attack methods can not effectively attack DNN-based radar object detection. To address the above problems, in this paper, we investigate the possibility of using a few adversarial objects to attack the DNN-based radar object detection models through passive reflection. These objects can be easily fabricated using 3D printing and metal foils at low cost. By placing these adversarial objects at some specific locations on a target vehicle, we can easily fool the victim AV's radar object detection model. The experimental results demonstrate that the attacker can achieve the attack goal by using only two adversarial objects and conceal them as car signs, which have good stealthiness and flexibility. To the best of our knowledge, this is the first study on the passive-reflection-based attacks against the DNN-based radar object detection models using low-cost, readily-available and easily concealable geometric shaped objects.

Background: Stroke is a major cause of long-term disability. While there is potential for improvements long after stroke onset, there is little to support functional recovery across the lifespan. mHealth solutions can help fill this gap. mRehab was designed to guide individuals with stroke through a home program and provide performance feedback. Objective: To examine if individuals with chronic stroke can use mRehab at home to improve upper limb mobility. The secondary objective was to examine if changes in limb mobility transferred to standardized clinical assessments. Methods: mRehab consists of a smartphone coupled with 3D printed household items: mug, bowl, key, and doorknob. The smartphone custom app guides task-oriented activities and measures both time to complete an activity and quality of movement (smoothness/accuracy). It also provides performance-based feedback to aid the user in self-monitoring their performance. Task-oriented activities were categorized as (1) object transportation, (2) prehensile grip with supination/pronation, (3) fractionated finger movement, and (4) walking with object. A total of 18 individuals with stroke enrolled in the single-subject experimental design study consisting of pretesting, a 6-week mRehab home program, and posttesting. Pre- and posttesting included both in-laboratory clinical assessments and in-home mRehab recorded samples of task performance. During the home program, mRehab recorded performance data. A System Usability Scale assessed user’s perception of mRehab. Results: A total of 16 participants completed the study and their data are presented in the results. The average days of exercise for each mRehab activity ranged from 15.93 to 21.19 days. This level of adherence was sufficient for improvements in time (t15=2.555, P=.02) and smoothness (t15=3.483, P=.003) in object transportation. Clinical assessments indicated improvements in functional performance (t15=2.675, P=.02) and hand dexterity (t15=2.629, P=.02). Participant’s perception of mRehab was positive. Conclusions: Despite heterogeneity in participants’ use of mRehab, there were improvements in upper limb mobility. Smartphone-based portable technology can support home rehabilitation programs in chronic conditions such as stroke. The ability to record performance data from home rehabilitation offers new insights into the impact of home programs on outcomes. Trial Registration: ClinicalTrials.gov NCT04363944; https://clinicaltrials.gov/ct2/show/NCT04363944

With the increasing deployment of voice-controlled devices in homes and enterprises, there is an urgent demand for voice identification to prevent unauthorized access to sensitive information and property loss. However, due to the broadcast nature of sound wave, a voice-only system is vulnerable to adverse conditions and malicious attacks. We observe that the cooperation of millimeter waves (mmWave) and voice signals can significantly improve the effectiveness and security of user identification. Based on the properties, we propose a multi-modal user identification system (named WavoID) by fusing the uniqueness of mmWave-sensed vocal vibration and mic-recorded voice of users. To estimate fine-grained waveforms, WavoID splits signals and adaptively combines useful decomposed signals according to correlative contents in both mmWave and voice. An elaborated anti-spoofing module in WavoID comprising biometric bimodal information defend against attacks. WavoID produces and fuses the response maps of mmWave and voice to improve the representation power of fused features, benefiting accurate identification, even facing adverse circumstances. We evaluate WavoID using commercial sensors on extensive experiments. WavoID has significant performance on user identification with over 98% accuracy on 100 user datasets.