Attacks on Voice Assistant Systems

Voice assistant systems (e.g., Siri, Alexa) have attracted wide research attention. However, such systems could receive voice information from malicious sources. Recent work has demonstrated that the voice authentication system is vulnerable to different types of attacks. The attacks are categorized into two main types: spoofing attacks and hidden voice commands. In this chapter, how to launch and defend such attacks is explored. For the spoofing attack, there are four main types, such as replay attacks, impersonation attacks, speech synthesis attacks, and voice conversion attacks. Although such attacks could be accurate on the speech recognition system, they could be easily identified by humans. Thus, the hidden voice commands have attracted a lot of research interest in recent years.

Voice User Interface: Literature review, challenges and future directions

Natural user interfaces are increasingly popular these days. One of the most common of these user interfaces today are voice-activated interfaces, in particular intelligent voice assistants such as Google Assistant, Alexa, Cortana and Siri. However, the results show that although there are many services available, there is still a lot to be done to improve the usability of these systems. Speech recognition, contextual understanding and human interaction are the issues that are not yet solved in this field. In this context, this research paper focuses on the state of the art and knowledge of work on intelligent voice interfaces, challenges and issues related to this field, in particular on interaction quality, usability, security and usability. As such, the study also examines voice assistant architecture components following the expansion of the use of technologies such as wearable computing in order to improve the user experience. Moreover, the presentation of new emerging technologies in this field will be the subject of a section in this work. The main contributions of this paper are therefore: (1) overview of existing research, (2) analysis and exploration of the field of intelligent voice assistant systems, with details at the component level, (3) identification of areas that require further research and development, with the aim of increasing its use, (4) various proposals for research directions and orientations for future work, and finally, (5) study of the feasibility of designing a new type of voice assistant and general presentation of the latter, whose realisation will be the subject of a thesis.

Multisensory Testing Framework for Advanced Driver Assistant Systems Supported by High-Quality 3D Simulation

ADAS and autonomous technologies in vehicles become more and more complex, which increases development time and expenses. This paper presents a new real-time ADAS multisensory validation system, which can speed up the development and implementation processes while lowering its cost. The proposed test system integrates a high-quality 3D CARLA simulator with a real-time-based automation platform. We present system experimental verifications on several types of sensors and testing system architectures. The first, open-loop experiment explains the real-time capabilities of the system based on the Mobileye 6 camera sensor detections. The second experiment runs a real-time closed-loop test of a lane-keeping algorithm (LKA) based on the Mobileye 6 line detection. The last experiment presents a simulation of Velodyne VLP-16 lidar, which runs a free space detection algorithm. Simulated lidar output is compared with the real lidar performance. We show that the platform generates reproducible results and allows closed-loop operation which, combined with a real-time collection of event information, promises good scalability toward complex ADAS or autonomous functionalities testing.

User Evaluation of Passenger Assistance System Concepts on Public Highways

There is ample research on assistance systems for drivers in conventional and automated vehicles. In the past, those systems were developed to increase safety but also to increase driver comfort. Since many common risks have by now been mitigated through such systems, the research and development focus expanded to also include comfort-related assistance. However, the passenger has rarely been taken into account explicitly, although it has been shown that passenger discomfort is a relevant problem. Therefore, this work investigated the potential of passenger assistance systems to reduce such discomfort. Three different passenger assistant system prototypes were tested in a driving study on public highway with N = 19 participants. The systems provided information about parameters related to the performance of the driver and one additionally provided a communicative means of influence. For two passenger assistant systems, it could be shown that they significantly reduced passenger discomfort in at least a subset of the evaluated situations. The majority of participants rated one or multiple of the assistant systems as more comfortable than a ride without assistance. The system providing information about the attentiveness of the driver was most effective in reducing discomfort and was rated as the most helpful system. The results show that explicitly considering the situation of passengers in the design of assistance systems can positively impact their comfort. This can be achieved using information from common systems targeting driver assistance available to the passenger.

Benefits and Barriers to Emerging Technologies to Promote Health, Well-Being, and Independence of Older Adults

Emerging technologies, such as voice assistant systems and artificial companion robots, hold a great deal of promise for improving the health, wellbeing, and independence of older adults. However, these solutions will likely be ineffective in the absence of research to understand barriers to the adoption and use of these technologies and without an exploration of the needs and preferences of older adults. This symposium focuses on both the potential of such technologies and factors that may affect their success. H. Spangler will present a detailed analysis of privacy concerns of older adults, with and without cognitive impairment, related to the use of Voice Assistant Systems (VAS). R. Nicholson will discuss the potential of a VAS app for promoting exercise among older adults and their caregivers to enhance mobility independence, with a focus on perceived benefits and dislikes about the app that may impact use. Finally, C. Berridge will present an exploration of perceptions of and attitudes toward artificial companion (AC) robots across the lifespan, before and after the start of the COVID-19 pandemic, including concerns about privacy. Together, these talks will highlight novel methods through which emerging technologies can support older adults and issues to consider if these methods are to produce meaningful change.

Privacy Concerns Among Older Adults Using Voice Assistant Systems

Voice Assistant Systems (VAS) are software platforms that complete various tasks using voice commands (e.g., Amazon Alexa), with increasing usage by older adults. It is unknown whether older adults have significant privacy concerns with VAS. 55 participants were evaluated from ambulatory practice sites for a study on VAS detection of early cognitive decline. The mean age was 73.3±5.6 years, 58% female, 93% white, and 53% had mild cognitive impairment. Privacy concerns were assessed via Likert-based surveys. Participants believed data was used with consent (71%) and stored properly (67%); however, 71% wanted new privacy regulations, 43% were comfortable with daily activity monitoring, and 85% thought the data needs to be highly protected. Qualitative themes included “listening-in”, “tracking”, and unwanted sharing of information. Findings suggest that older adults do not have significant privacy concerns for VAS use, but requested additional regulations. Future research can compare VAS privacy concerns between age groups.

Co-DAS: Development and Evaluation of Co-Driver Assistance System Concepts to Reduce Passenger Discomfort

The front seat passenger is often neglected when developing support systems for cars. There exist few examples of systems that provide information or interaction possibilities specifically to those passengers. Previous research indicated that the passive role of the passenger can frequently lead to a feeling of discomfort, potentially caused by missing information and missing control with respect to the driving situation. This paper proposes a variety of prototypical passenger assistance systems that target different aspects of the cognitive processes which could cause the feeling of discomfort. In a simulator study with N = 40 participants, these systems were investigated with respect to their influence on measures of discomfort. Participants experienced different car following and braking scenarios on the highway with different time headways, with and without one of the passenger assistance systems. Based on the subjective measures, three systems were identified as particularly useful in reducing discomfort. For the best of these proposals, more than 63 % of the passengers confirmed the usefulness of the approach and reported an interest in using it in their vehicle. This demonstrates significant opportunities to improve the everyday driving experience beyond classical assistant systems by explicitly taking into account the needs of the passengers.

Human–Machine Interaction in Driving Assistant Systems for Semi-Autonomous Driving Vehicles

Currently, the existing vehicle-centric semi-autonomous driving modules do not consider the driver’s situation and emotions. In an autonomous driving environment, when changing to manual driving, human–machine interface and advanced driver assistance systems (ADAS) are essential to assist vehicle driving. This study proposes a human–machine interface that considers the driver’s situation and emotions to enhance the ADAS. A 1D convolutional neural network model based on multimodal bio-signals is used and applied to control semi-autonomous vehicles. The possibility of semi-autonomous driving is confirmed by classifying four driving scenarios and controlling the speed of the vehicle. In the experiment, by using a driving simulator and hardware-in-the-loop simulation equipment, we confirm that the response speed of the driving assistance system is 351.75 ms and the system recognizes four scenarios and eight emotions through bio-signal data.

Study on cutting force of reaming porcine bone and substitute bone

Accurate mechanical feedback systems are critical to the successful implementation of virtual and robotic surgical assistant systems. Experimental measurements of reaming force could further our understanding of the cancellous bone reaming process during hip arthroplasty to help develop surgical simulators with realistic force effects and improve the protection mechanism of robot-assisted surgical systems. In this study, reaming experiments with natural bone (porcine femur) and a bone substitute (polyurethane blocks) were performed on a CNC lathe. This paper proposes using the maximum reaming force of the steady reaming stage to represent the force characteristic. The reaming force is biased to one side in the overlap direction and the maximum reaming force will vary when the reamer is not coincident with the long axis of the bone. The diameter of the reamer has the greatest influence on reaming force, which clearly increases with increasing reamer diameter. During operation, a medium rotation speed and high feed speed can reduce the reaming force. After cutting, the morphology of the cut surface is not flat, but arc-shaped, which will have a significant impact on implantation of the femoral prosthesis. In in vitro cutting experiments, polyurethane blocks can be used as a substitute for cancellous bone.