Search for: All records

Modern smart buildings and environments rely on sensory infrastructure to capture and process information about their inhabitants. However, it remains challenging to ensure that this infrastructure complies with privacy norms, preferences, and regulations; individuals occupying smart environments are often occupied with their tasks, lack awareness of the surrounding sensing mechanisms, and are non-technical experts. This problem is only exacerbated by the increasing number of sensors being deployed in these environments, as well as services seeking to use their sensory data. As a result, individuals face an unmanageable number of privacy decisions, preventing them from effectively behaving as their own “privacy firewall” for filtering and managing the multitude of personal information flows. These decisions often require qualitative reasoning over privacy regulations, understanding privacy-sensitive contexts, and applying various privacy transformations when necessary We propose the use of Large Language Models (LLMs), which have demonstrated qualitative reasoning over social/legal norms, sensory data, and program synthesis, all of which are necessary for privacy firewalls. We present PrivacyOracle, a prototype system for configuring privacy firewalls on behalf of users using LLMs, enabling automated privacy decisions in smart built environments. Our evaluation shows that PrivacyOracle achieves up to 

Mobile devices with dynamic refresh rate (DRR) switching displays have recently become increasingly common. For power optimization, these devices switch to lower refresh rates when idling, and switch to higher refresh rates when the content displayed requires smoother transitions. However, the security and privacy vulnerabilities of DRR switching have not been investigated properly. In this paper, we propose a novel attack vector called RefreshChannels that exploits DRR switching capabilities for mobile device attacks. Specifically, we first create a covert channel between two colluding apps that are able to stealthily share users' private information by modulating the data with the refresh rates, bypassing the OS sandboxing and isolation measures. Second, we further extend its applicability by creating a covert channel between a malicious app and either a phishing webpage or a malicious advertisement on a benign webpage. Our extensive evaluations on five popular mobile devices from four different vendors demonstrate the effectiveness and widespread impacts of these attacks. Finally, we investigate several countermeasures, such as restricting access to refresh rates, and find they are inadequate for thwarting RefreshChannels due to DDR's unique characteristics 

This paper investigates the challenges posed by delays in Closed-Loop Sense-Act Systems in the context of Adversarial Internet of Things (IoT) applications. Prior work focused on studying the impact of delays on a single resource-constrained platform. To capitalize on the capabilities of different computing platforms, this work investigates the adaptation of control placement to optimize application performance in distributed settings. An Adaptive Control Placement (ACP) strategy is introduced, which dynamically switches between a local controller with lower accuracy and a cloud controller with higher accuracy based on network dynamics, optimizing overall application performance. The effectiveness of the ACP strategy is evaluated using a simulated Vehicle Following application in the PyBullet simulator. The results demonstrate that in terms of a time-to-complete (TTC) metric, the ACP strategy consistently outperforms strategies that use a fixed combination of controller type and location (e.g., PID at Local and MPC at Cloud) across various deadline scenarios. 

Wearable devices like smartwatches and smart wristbands have gained substantial popularity in recent years. However, their small interfaces create inconvenience and limit computing functionality. To fill this gap, we propose ViWatch, which enables robust finger interactions under deployment variations, and relies on a single IMU sensor that is ubiquitous in COTS smartwatches. To this end, we design an unsupervised Siamese adversarial learning method. We built a real-time system on commodity smartwatches and tested it with over one hundred volunteers. Results show that the system accuracy is about 97% over a week. In addition, it is resistant to deployment variations such as different hand shapes, finger activity strengths, and smartwatch positions on the wrist. We also developed a number of mobile applications using our interactive system and conducted a user study where all participants preferred our unsupervised approach to supervised calibration. The demonstration of ViWatch is shown at https://youtu.be/N5-ggvy2qfI. 

As augmented and virtual reality (AR/VR) technology matures, a method is desired to represent real-world persons visually and aurally in a virtual scene with high fidelity to craft an immersive and realistic user experience. Current technologies leverage camera and depth sensors to render visual representations of subjects through avatars, and microphone arrays are employed to localize and separate high-quality subject audio through beamforming. However, challenges remain in both realms. In the visual domain, avatars can only map key features (e.g., pose, expression) to a predetermined model, rendering them incapable of capturing the subjects’ full details. Alternatively, high-resolution point clouds can be utilized to represent human subjects. However, such three-dimensional data is computationally expensive to process. In the realm of audio, sound source separation requires prior knowledge of the subjects’ locations. However, it may take unacceptably long for sound source localization algorithms to provide this knowledge, which can still be error-prone, especially with moving objects. These challenges make it difficult for AR systems to produce real-time, high-fidelity representations of human subjects for applications such as AR/VR conferencing that mandate negligible system latency. We present Acuity, a real-time system capable of creating high-fidelity representations of human subjects in a virtual scene both visually and aurally. Acuity isolates subjects from high-resolution input point clouds. It reduces the processing overhead by performing background subtraction at a coarse resolution, then applying the detected bounding boxes to fine-grained point clouds. Meanwhile, Acuity leverages an audiovisual sensor fusion approach to expedite sound source separation. The estimated object location in the visual domain guides the acoustic pipeline to isolate the subjects’ voices without running sound source localization. Our results demonstrate that Acuity can isolate multiple subjects’ high-quality point clouds with a maximum latency of 70 ms and average throughput of over 25 fps, while separating audio in less than 30 ms. We provide the source code of Acuity at: https://github.com/nesl/Acuity. 

Existing approaches for autonomous control of pan-tilt-zoom (PTZ) cameras use multiple stages where object detection and localization are performed separately from the control of the PTZ mechanisms. These approaches require manual labels and suffer from performance bottlenecks due to error propagation across the multi-stage flow of information. The large size of object detection neural networks also makes prior solutions infeasible for real-time deployment in resource-constrained devices. We present an end-to-end deep reinforcement learning (RL) solution called Eagle1 to train a neural network policy that directly takes images as input to control the PTZ camera. Training reinforcement learning is cumbersome in the real world due to labeling effort, runtime environment stochasticity, and fragile experimental setups. We introduce a photo-realistic simulation framework for training and evaluation of PTZ camera control policies. Eagle achieves superior camera control performance by maintaining the object of interest close to the center of captured images at high resolution and has up to 17% more tracking duration than the state-of-the-art. Eagle policies are lightweight (90x fewer parameters than Yolo5s) and can run on embedded camera platforms such as Raspberry PI (33 FPS) and Jetson Nano (38 FPS), facilitating real-time PTZ tracking for resource-constrained environments. With domain randomization, Eagle policies trained in our simulator can be transferred directly to real-world scenarios2. 

Machine learning at the extreme edge has enabled a plethora of intelligent, time-critical, and remote applications. However, deploying interpretable artificial intelligence systems that can perform high-level symbolic reasoning and satisfy the underlying system rules and physics within the tight platform resource constraints is challenging. In this paper, we introduceTinyNS, the first platform-aware neurosymbolic architecture search framework for joint optimization of symbolic and neural operators.TinyNSprovides recipes and parsers to automatically write microcontroller code for five types of neurosymbolic models, combining the context awareness and integrity of symbolic techniques with the robustness and performance of machine learning models.TinyNSuses a fast, gradient-free, black-box Bayesian optimizer over discontinuous, conditional, numeric, and categorical search spaces to find the best synergy of symbolic code and neural networks within the hardware resource budget. To guarantee deployability,TinyNStalks to the target hardware during the optimization process. We showcase the utility ofTinyNSby deploying microcontroller-class neurosymbolic models through several case studies. In all use cases,TinyNSoutperforms purely neural or purely symbolic approaches while guaranteeing execution on real hardware.

 

Inertial navigation provides a small footprint, low-power, and low-cost pathway for localization in GPS-denied environments on extremely resource-constrained Internet-of-Things (IoT) platforms. Traditionally, application-specific heuristics and physics-based kinematic models are used to mitigate the curse of drift in inertial odometry. These techniques, albeit lightweight, fail to handle domain shifts and environmental non-linearities. Recently, deep neural-inertial sequence learning has shown superior odometric resolution in capturing non-linear motion dynamics without human knowledge over heuristic-based methods. These AI-based techniques are data-hungry, suffer from excessive resource usage, and cannot guarantee following the underlying system physics. This paper highlights the unique methods, opportunities, and challenges in porting real-time AI-enhanced inertial navigation algorithms onto IoT platforms. First, we discuss how platform-aware neural architecture search coupled with ultra-lightweight model backbones can yield neural-inertial odometry models that are 31–134 x smaller yet achieve or exceed the localization resolution of state-of-the-art AI-enhanced techniques. The framework can generate models suitable for locating humans, animals, underwater sensors, aerial vehicles, and precision robots. Next, we showcase how techniques from neurosymbolic AI can yield physics-informed and interpretable neural-inertial navigation models. Afterward, we present opportunities for fine-tuning pre-trained odometry models in a new domain with as little as 1 minute of labeled data, while discussing inexpensive data collection and labeling techniques. Finally, we identify several open research challenges that demand careful consideration moving forward. 

Precision agricultural robots require high-resolution navigation solutions. In this paper, we introduce a robust neural-inertial sequence learning approach to track such robots with ultra-intermittent GNSS updates. First, we propose an ultra-lightweight neural-Kalman filter that can track agricultural robots within 1.4 m (1.4–5.8× better than competing techniques), while tracking within 2.75 m with 20 mins of GPS outage. Second, we introduce a user-friendly video-processing toolbox to generate high-resolution (±5 cm) position data for fine-tuning pre-trained neural-inertial models in the field. Third, we introduce the first and largest (6.5 hours, 4.5 km, 3 phases) public neural-inertial navigation dataset for precision agricultural robots. The dataset, toolbox, and code are available at: https://github.com/nesl/agrobot.