Search

The promise of Brain-Computer Interfaces (BCIs) is counterbalanced by concerns about vulnerabilities. Recent studies have revealed that EEG-based BCIs are susceptible to security breaches. However, current attack approaches are challenging to execute in real-world settings because they need access to, at a minimum, the EEG data stream. In this work, we introduce an unexplored vulnerability of current EEG-based BCIs that consists of remotely injecting false brain-waves into the recording device. We do this by transmitting amplitude-modulated radio-frequency (RF) signals that are received by the physical structure of the EEG equipment. We demonstrate the versatility of our system by successfully attacking three different categories of EEG devices: research-grade (Neuroelectrics), open-source (OpenBCI), and consumer-grade (Muse). We test our attack system by taking control of three different BCIs: a virtual keyboard speller, a drone-control interface, and a neuro-feedback meditation interface. Our system was successful in each case, forcing the input of any desired character with the virtual keyboard, crashing the drone, and reporting false meditative states, respectively. To the best of our knowledge, this is the first time that an EEG device is remotely hacked at the physical layer. This work shows the risks that can arise from this type of attacks, which can not only be dangerous by seizing control of a BCI, but could also lead to severe misdiagnoses in clinical EEG tests.

© 2020 SPIE. We propose a generalized, modular, closed-loop system for objective assessment of human visual parameters. Our system presents periodical visual stimuli to the patient's field of view and analyses the consequent evoked brain potentials elicited in the occipital lobe and recorded through EEG. The analysis of the monitored EEG data is performed in an end-to-end fashion by a convolutional neural network (CNN). We propose a novel CNN architecture for EEG signal analysis that can be trained utilizing the benefits of multi-task learning. The closedloop attribute of our system allows for a real-time adaptation of the subsequent stimuli to further examine a potentially damaged area or increase the granularity of the exploration. Interchangeability is provided in terms of software modules, stimulus type, visual hardware, EEG acquisition device and EEG electrodes. Initially, the system is designed to monitor visual field loss originating from glaucoma or damage to the optic nerve using a virtual reality (VR) headset for the stimuli presentation. The modular architecture of our system paves the way for the assessment and monitoring of other neuro-visual functions.

In this work we present Sublime, a new concept of Steady-State Visually Evoked Potential (SSVEP) based Brain-Computer Interface (BCI) where brain-computer communication occurs by capturing imperceptible visual stimuli integrated in the virtual scene and effortlessly conveying subliminal information to a computer. The technology was tested in a Virtual Reality (VR) environment, where the subject could navigate between the different menus by just gazing at them. The ratio between the stimuli frequencies and the refresh rate of the VR display creates an undesired perception of beats for which different solutions are proposed. To inform the user of target activation, real-time feedback in the form of loading bars is incorporated under each selectable object. We conducted experiments with several subjects and though the system is slower than a conventional joystick, users reported a satisfactory overall experience, in part due to the unexpected responsiveness of the system, as well as due to the fact that virtual objects flickered at a rate that did not cause annoyance. Since the imperceptible visual stimuli can be integrated unobtrusively to any element of the virtual world, we conclude that the potential applications of Sublime are extensive, especially in situations where knowing user’s visual focus can be relevant.

We present an Augmented Reality (AR) visualization and interaction tool for users to control Internet of Things (IoT) devices with hand gestures. Today, smart IoT devices are becoming increasingly ubiquitous with diverse forms and functions, yet most user controls over them are still limited to mobile devices and web interfaces. Recently, AR has been developed rapidly, and provided immersive solutions to enhance user experience of applications in many fields. Its capability to create immersive interactions allows AR to improve the way smart devices are controlled via more direct visual feedback. In this paper, we create a functional prototype of one such system, enabling seamless interactions with sound and lighting systems through the use of augmented hand-controlled interaction panels. To interpret users' intentions, we implement a standard 2D convolution neural network (CNN) for real-time hand gesture recognition and deploy it within our system. Our prototype is also equipped with a simple but effective object detector which can identify target devices within a proper range by analyzing geometric features. We evaluate the performance of our system qualitatively and quantitatively and demonstrate it on two smart devices.

Augmented Reality (AR) is known to enhance user experience, however, it remains under-adopted in industry. We present an AR interaction system improving human-machine coordination in Internet of Things (IoT) and Industry 4.0 applications including manufacturing and assembly, maintenance and safety, and other highly-interactive functions. A driver of slow adoption is the computational complexity and inaccuracy in localization and rendering digital content. AR systems may render digital content close to the associated physical objects, but traditional object recognition and localization modules perform poorly when tracking texture-less objects and complex shapes, presenting a need for robust and efficient digital content rendering techniques. We propose a method of improving IoT-AR by integrating Deep Learning with AR to increase accuracy and robustness of the target object localization module, taking both color and depth images as input and outputting the target's pose parameters. Quantitative and qualitative experiments prove this system's efficacy and show potential for fusing these emerging technologies in real-world applications.

Thesis: S.M., Massachusetts Institute of Technology, Department of Mechanical Engineering, 2018., Cataloged from PDF version of thesis., Includes bibliographical references (pages 67-72)., The growing Internet of Things (JoT) ecosystem being built today is already affecting a great many daily objects, which may share information about their state, location and sensed data among others. Today, humans communicate with IoT devices through visual, voice or tactile interfaces. More natural and organic interaction requires more sophisticated communication methods. This thesis explores seamless interfaces between human and IoT devices. In particular, I focus on using biological signals as the interface to directly connect with the smart surroundings. The work is partitioned in two parts. First, I present a wearable sensing system to estimate the thermal comfort level of the user by monitoring skin temperature, blood volume pressure and skin conductivity. This effort is a first step towards connecting room occupants and smart A/C devices, which can enable real-time adjustments of indoor conditions. In the second part of the thesis, brain signals are used as the interface to navigate in a Virtual Reality (VR) environment. We develop Sublime, a new concept of Steady-State Visually Evoked Potentials (SSVEP) based Brain-Computer Interface (BCI). In this technology, brain-computer communication is triggered by imperceptible visual stimuli integrated in the virtual scene and subliminal information is seamlessly conveyed to a computer. By monitoring the elicited SSVEPs, the system is able to identify the gaze target of the user, thus enabling a hands-free menu navigation tool., by Alexandre Armengol Urpi., S.M.