The rapid development of large language models (LLMs) has significantly advanced code completion capabilities, giving rise to a new generation of LLM-based Code Completion Tools (LCCTs). Unlike general-purpose LLMs, these tools possess unique workflows, integrating multiple information sources as input and prioritizing code suggestions over natural language interaction, which introduces distinct security challenges. Additionally, LCCTs often rely on proprietary code datasets for training, raising concerns about the potential exposure of sensitive data. This paper exploits these distinct characteristics of LCCTs to develop targeted attack methodologies on two critical security risks: jailbreaking and training data extraction attacks. Our experimental results expose significant vulnerabilities within LCCTs, including a 99.4% success rate in jailbreaking attacks on GitHub Copilot and a 46.3% success rate on Amazon Q. Furthermore, We successfully extracted sensitive user data from GitHub Copilot, including 54 real email addresses and 314 physical addresses associated with GitHub usernames. Our study also demonstrates that these code-based attack methods are effective against general-purpose LLMs, highlighting a broader security misalignment in the handling of code by modern LLMs. These findings underscore critical security challenges associated with LCCTs and suggest essential directions for strengthening their security frameworks.

Weight difference estimation is crucial in various applications, particularly for identifying items being picked up and put back when people interact with the shelf while shopping in autonomous stores, ensuring precise cost estimation. However, the conventional approach of estimating weight changes requires specialized weight-sensing shelves, which are densely deployed weight scales, incurring intensive sensor consumption and maintenance costs. Prior works explored the vibration-based weight sensing method, but they are limited to the object that can generate vibration through motion. This work demonstrates a system leveraging active vibration sensing for weight difference estimation on shelves at different locations. The main intuition of the system is that the weight placed on the shelf influences the dynamic vibration response of the shelf, thus altering the shelf vibration patterns. Our system achieves a mean absolute error 9.23 grams and mean absolute percentage error 7.9% on the real-store shelf layout.

Vibrometry-based side channels pose a significant privacy risk, exploiting sensors like mmWave radars, light sensors, and accelerometers to detect vibrations from sound sources or proximate objects, enabling speech eavesdropping. Despite various proposed defenses, these involve costly hard-ware solutions with inherent physical limitations. This paper presents EveGuard, a software-driven defense framework that creates adversarial audio, protecting voice privacy from side channels without compromising human perception. We leverage the distinct sensing capabilities of side channels and traditional microphones-where side channels capture vibrations and microphones record changes in air pressure, resulting in different frequency responses. EveGuard first proposes a perturbation generator model (PGM) that effectively suppresses sensor-based eavesdropping while maintaining high audio quality. Second, to enable end-to-end training of PGM, we introduce a new domain translation task called Eve-GAN for inferring an eavesdropped signal from a given audio. We further apply few-shot learning to mitigate the data collection overhead for Eve-GAN training. Our extensive experiments show that EveGuard achieves a protection rate of more than 97% from audio classifiers and significantly hinders eaves-dropped audio reconstruction. We further validate the performance of EveGuard across three adaptive attack mechanisms. We have conducted a user study to verify the perceptual quality of our perturbed audio.

Figure 1: UltraPoser enables ubiquitous full-body pose estimation by integrating ultrasound sensing and IMU using commodity wearable devices.In addition to measuring IMU data, a smartphone and smartwatch are used to transmit and receive ultrasound signals.The extracted ultrasound features capture motions from joints without any attached devices and offer drift-free range measurements to complement IMU data for more accurate pose estimation.

Accurate and responsive simulation of radio frequency (RF) signal propagation is crucial for designing wireless systems operating in dynamic environments. Conventional ray tracing approaches struggle to accurately model the intricate geometries and material properties of objects that impact propagation. Recently proposed neural scene representations can learn such intricacies from RF data, but they treat the entire scene as implicit neural networks, necessitating retraining with a massive amount of RF data upon any environmental changes. In this paper, we propose RFCanvas, which fuses visual priors and RF measurements to achieve high accuracy for realistic scenes and be responsive to environmental changes. To ensure compatibility between visual priors and RF measurements, we introduce RFCanvas scene representations that model shapes and materials of substantial objects with tensorial fields and signed distance fields. We further extract motion information from visual priors to adapt RFCanvas scene representations to scene dynamics. RFCanvas is built upon an end-to-end optimization framework with differentiable RF simulation. Extensive evaluations across real-world wireless communication and sensing environments demonstrate RFCanvas's superiority over both existing methods.

Acoustic ranging has been viewed as a promising Human-Computer Interaction (HCI) technology in many scenarios, such as Augmented Reality (AR)/Virtual Reality (VR) and smart appliances. Most ranging systems with distributed devices undergo an extra calibration process to remove the timing errors. However, the calibration process needs user intervention. Furthermore, it should assume that the clock drifts are linear and stable, which is disabled within tens of minutes. In this paper, we introduce a self-calibrated acoustic ranging system that achieves sub-millimeter accuracy on distributed asynchronous devices. Based on our theoretical timing model, we precisely cancel both the system delay and the nonlinear clock drift with carefully designed Orthogonal Frequency-Division Multiplexing (OFDM) ranging signals. Our synchronization scheme achieves a timing accuracy of 1.9 microseconds, which allows us to build large-scale virtual acoustic arrays. Based on such a calibration scheme, our localization system achieves a ranging error of$\rm{0.39}~mm$within three meters in real-world experiments.

Accurately reconstructing 3D hand poses is a pivotal element for numerous Human-Computer Interaction applications. In this work, we propose SonicHand, the first smartphone-based 3D hand pose reconstruction system using purely inaudible acoustic signals. SonicHand incorporates signal processing techniques and a deep learning framework to address a series of challenges. First, it encodes the topological information of the hand skeleton as prior knowledge and utilizes a deep learning model to realistically and smoothly reconstruct the hand poses. Second, the system employs adversarial training to enhance the generalization ability of our system to be deployed in a new environment or for a new user. Third, we adopt a hand tracking method based on channel impulse response estimation. It enables our system to handle the scenario where the hand performs gestures while moving arbitrarily as a whole. We conduct extensive experiments on a smartphone testbed to demonstrate the effectiveness and robustness of our system from various dimensions. The experiments involve 10 subjects performing up to 12 different hand gestures in three distinctive environments. When the phone is held in one of the user’s hands, the proposed system can track joints with an average error of 18.64 mm.

In this paper, we propose a Dynamic Speed Warping (DSW) algorithm to enable one-shot learning for device-free acoustic gesture signals performed by different users. The design of DSW is based on the observation that the gesture type is determined by the trajectory of hand components rather than the movement speed. By dynamically scaling the speed distribution and tracking the movement distance along the trajectory, DSW can effectively match gesture signals from different domains with a ten-fold difference in speeds. Our experimental results show that DSW can achieve a recognition accuracy of 97% for gestures performed by unknown users while only using one training sample of each gesture type from four training users.

Immersive face-to-virtual-face telecommunication is one unique use case for virtual reality (VR) technologies. Existing camera-based telephony systems cannot be used for such immersive VR video chat, due to the physical occlusions of head-mounted displays (HMDs) and/or unwieldy positioning of cameras. To address these, we present ExGSense, a new VR input modality that can sense and reconstruct both upper and lower facial gestures, by only using lightweight biopotential sensors embedded within the HMDs. We optimize the sensor arrangement based on facial anatomy and employ a multiview classification pipeline to exploit the multiple dimensions of signal features. We thus enable ExGSense to detect whole facial gestures by using a sparse set of biopotential transducers. We prototyped ExGSense and evaluated its performance with 42 facial gestures and across different users. We showed a 93% accuracy for user-specific evaluation, and 77% accuracy for user-independent evaluation with low calibration overhead. We believe ExGSense constitutes a promising input modality for immersive VR interactions.

Robust speech enhancement is considered as the holy grail of audio processing and a key requirement for human-human and human-machine interaction. Solving this task with single-channel, audio-only methods remains an open challenge, especially for practical scenarios involving a mixture of competing speakers and background noise. In this paper, we propose UltraSE, which uses ultrasound sensing as a complementary modality to separate the desired speaker's voice from interferences and noise. UltraSE uses a commodity mobile device (e.g., smartphone) to emit ultrasound and capture the reflections from the speaker's articulatory gestures. It introduces a multi-modal, multi-domain deep learning framework to fuse the ultrasonic Doppler features and the audible speech spectrogram. Furthermore, it employs an adversarially trained discriminator, based on a cross-modal similarity measurement network, to learn the correlation between the two heterogeneous feature modalities. Our experiments verify that UltraSE simultaneously improves speech intelligibility and quality, and outperforms state-of-the-art solutions by a large margin.

This paper studies the problem of cHarging tAskScheduling for direcTional wireless chargEr networks (HASTE), i.e., given a set of rotatable directional wireless chargers on a 2D area and a series of offline (online) charging tasks, scheduling the orientations of all the chargers with time in a centralized offline (distributed online) fashion to maximize the overall charging utility for all the tasks. We prove that HASTE is NP-hard. Then, we prove that a relaxed version of HASTE falls within the realm of maximizing a submodular function subject to a partition matroid constraint, and propose a centralized offline algorithm that achieves$(1-\rho)(1-\frac{1}{e})$approximation ratio to address HASTE where$\rho$is the switching delay of chargers. Further, we propose a distributed online algorithm and prove it achieves$\frac{1}{2}(1-\rho)(1-\frac{1}{e})$competitive ratio. We conduct simulations and field experiments on a testbed consisting of eight off-the-shelf power transmitters and 8 rechargeable sensor nodes. The results show that our distributed online algorithm achieves 92.97 percent of the optimal charging utility, and outperforms the comparison algorithms by up to 15.28 percent in terms of charging utility.

Gesture tracking is a basic Human-Computer Interaction mechanism to control devices, such as IoT and VR/AR devices. However, prior OFDM signal based systems focus on gesture recognition and provide results with insufficient accuracy, and thus, cannot be applied for high-precision gesture tracking. In this paper, we propose a CSI based device-free gesture tracking system, called WiTrace, which leverages the CSI values extracted from OFDM signals to enable accurate gesture tracking. For 1D tracking, WiTrace derives the phase of the signals reflected by the hand from the composite signals, and measures the phase changes to obtain the movement distance. For 2D tracking, WiTrace proposes the first CSI based scheme to accurately estimate the initial position, and adopts the Kalman Filter based on continuous Wiener process acceleration model to further filter out tracking noise. Our results show that WiTrace achieves an average accuracy of 6.23 cm for initial position estimation and achieves cm-level accuracy with average tracking errors of 1.46 cm and 2.09 cm for 1D tracking and 2D tracking, respectively.

Cellular network operators deploy base stations with a high density to ensure radio signal coverage for 4G/5G networks. While users enjoy the high-speed connection provided by cellular networks, an adversary could exploit the dense cellular deployment to detect nearby human movements and even recognize keystroke movements of a victim by passively listening to the CRS broadcast from base stations. To demonstrate this, we develop SpiderMon, the first attempt to perform passive continuous keystroke monitoring using the signal transmitted by commercial cellular base stations. Our experimental results show that SpiderMon can detect keystroke movements at a distance of 15 meters and can recover a 6-digits PIN input with a success rate of more than 51% within ten trials when the victim is behind the wall.

In this paper, we propose a Dynamic Speed Warping (DSW) algorithm to enable one-shot learning for device-free gesture signals performed by different users. The design of DSW is based on the observation that the gesture type is determined by the trajectory of hand components rather than the movement speed. By dynamically scaling the speed distribution and tracking the movement distance along the trajectory, DSW can effectively match gesture signals from different domains that have a ten-fold difference in speeds. Our experimental results show that DSW can achieve a recognition accuracy of 97% for gestures performed by unknown users, while only use one training sample of each gesture type from four training users.

Many human activities involve interactions with passive objects. By wirelessly sensing human interactions with such "things", one can infer activities at a fine resolution, enabling a new wave of ubiquitous applications. This forms the basis of the tangible user interface allowing individual to use omnipresent objects as a control interface to the digital world. Existing works have tendencies to create such interface with complicated circuitry, leading to overwhelm complexities. To conquer these, we propose the inkjet printable capacitive tags (CapTags), empowering a new paradigm of printable communications and sensing modality. We use discrete capacitive and inductive components to simulate the tag-interrogator system, and prove the feasibility of proposed hardware featurization and high frequency sweeping strategy where the information can be encoded in the resonating spikes. This enables the touch points to be detected by searching resonating detune effects. Although this work only includes the designs and simulations, we believe this new sensing modality would truly realize the vision of printable ubiquitous computing.

Robust and accurate trajectory estimation of mobile agents such as people and robots is a key requirement for providing spatial awareness for emerging capabilities such as augmented reality or autonomous interaction. Although currently dominated by optical techniques e.g., visual-inertial odometry these suffer from challenges with scene illumination or featureless surfaces. As an alternative, we propose milliEgo, a novel deep-learning approach to robust egomotion estimation which exploits the capabilities of low-cost mm Wave radar. Although mmWave radar has a fundamental advantage over monocular cameras of being metric i.e., providing absolute scale or depth, current single chip solutions have limited and sparse imaging resolution, making existing point-cloud registration techniques brittle. We propose a new architecture that is optimized for solving this challenging pose transformation problem. Secondly, to robustly fuse mmWave pose estimates with additional sensors, e.g. inertial or visual sensors we introduce a mixed attention approach to deep fusion. Through extensive experiments, we demonstrate our proposed system is able to achieve 1.3% 3D error drift and generalizes well to unseen environments. We also show that the neural architecture can be made highly efficient and suitable for real-time embedded applications.

Voice assistants (VAs) are becoming highly popular recently as a general means of interacting with the Internet of Things. However, the use of always-on microphones on VAs imposes a looming threat on users' privacy. In this paper, we propose MicShield, the first system that serves as a companion device to enforce privacy preservation on VAs. MicShield introduces a novel selective jamming mechanism, which obfuscates the user's private speech while passing legitimate voice commands to the VAs. It achieves this by using a phoneme level jamming control pipeline. Our implementation and experiments demonstrate that MicShield can effectively protect a user's private speech, without affecting the VA's responsiveness.

This paper studies the problem of cHarging tAsk Scheduling for direcTional wireless chargEr networks (HASTE), i.e., given a set of rotatable directional wireless chargers on a 2D area and a series of offline (online) charging tasks, scheduling the orientations of all the chargers with time in a centralized offline (distributed online) fashion to maximize the overall charging utility for all the tasks. We prove that HASTE is NP-hard. Then, we prove that a relaxed version of HASTE falls within the realm of maximizing a submodular function subject to a partition matroid constraint, and propose a centralized offline algorithm that achieves (1-ρ)(1-1/e) approximation ratio to address HASTE where ρ is the switching delay of chargers. Further, we propose a distributed online algorithm and prove it achieves 1/2(1-ρ)(1-1/e) competitive ratio. We conduct simulations, and field experiments on a testbed consisting of 8 off-the-shelf power transmitters and 8 rechargeable sensor nodes. The results show that our distributed online algorithm achieves 92.97% of the optimal charging utility, and outperforms the comparison algorithms by up to 26.19% in terms of charging utility.

Enabling touch gesture sensing on all surfaces of the mobile device, not limited to the touchscreen area, leads to new user interaction experiences. In this paper, we propose VSkin, a system that supports fine-grained gesture-sensing on the back of mobile devices based on acoustic signals. VSkin utilizes both the structure-borne sounds, i.e., sounds propagating through the structure of the device, and the air-borne sounds, i.e., sounds propagating through the air, to sense finger tapping and movements. By measuring both the amplitude and the phase of each path of sound signals, VSkin detects tapping events with an accuracy of 99.65% and captures finger movements with an accuracy of 3.59mm.

For AR/VR systems, tapping-in-the-air is a user-friendly solution for interactions. Most prior in-air tapping schemes use customized depth-cameras and therefore have the limitations of low accuracy and high latency. In this paper, we propose a fine-grained depth-aware tapping scheme that can provide high accuracy tapping detection. Our basic idea is to use light-weight ultrasound based sensing, along with one COTS mono-camera, to enable 3D tracking of user's fingers. The mono-camera is used to track user's fingers in the 2D space and ultrasound based sensing is used to get the depth information of user's fingers in the 3D space. Using speakers and microphones that already exist on most AR/VR devices, we emit ultrasound, which is inaudible to humans, and capture the signal reflected by the finger with the microphone. From the phase changes of the ultrasound signal, we accurately measure small finger movements in the depth direction. With fast and light-weight ultrasound signal processing algorithms, our scheme can accurately track finger movements and measure the bending angle of the finger between two video frames. In our experiments on eight users, our scheme achieves a 98.4% finger tapping detection accuracy with FPR of 1.6% and FNR of 1.4%, and a detection latency of 17.69ms, which is 57.7ms less than video-only schemes. The power consumption overhead of our scheme is 48.4% more than video-only schemes.

Gesture tracking is a basic Human-Computer Interaction mechanism to control devices such as electronic Internet of Things and VR/AR devices. However, prior WiFi signal based systems focus on gesture recognition and provide results with insufficient accuracy, and thus cannot be applied for highprecision gesture tracking. In this paper, we propose a CSI based device-free gesture tracking system, called WiTrace, which leverages the CSI values extracted from WiFi signals to enable accurate gesture tracking. For 1D tracking, WiTrace derives the phase of the signals reflected by the hand from the composite signals, and measures the phase changes to obtain the movement distance. For 2D tracking, WiTrace proposes the first CSI based scheme to accurately estimate the initial position, and adopts the Kalman filter based on Continuous Wiener Process Acceleration model to further filter out tracking noise. Our results show that WiTrace achieves the estimated accuracy of 3.91 cm for initial position on average, and achieves cm-level accuracy, with mean tracking errors of 1.46 cm and 2.09 cm for 1D tracking and 2D tracking, respectively.

Device-free gesture tracking is an enabling HCI mechanism for small wearable devices because fingers are too big to control the GUI elements on such small screens, and it is also an important HCI mechanism for medium-to-large size mobile devices because it allows users to provide input without blocking screen view. In this paper, we propose LLAP, a device-free gesture tracking scheme that can be deployed on existing mobile devices as software, without any hardware modification. We use speakers and microphones that already exist on most mobile devices to perform device-free tracking of a hand/finger. The key idea is to use acoustic phase to get fine-grained movement direction and movement distance measurements. LLAP first extracts the sound signal reflected by the moving hand/finger after removing the background sound signals that are relatively consistent over time. LLAP then measures the phase changes of the sound signals caused by hand/finger movements and then converts the phase changes into the distance of the movement. We implemented and evaluated LLAP using commercial-off-the-shelf mobile phones. For 1-D hand movement and 2-D drawing in the air, LLAP has a tracking accuracy of 3.5 mm and 4.6 mm, respectively. Using gesture traces tracked by LLAP, we can recognize the characters and short words drawn in the air with an accuracy of 92.3% and 91.2%, respectively.

In this demo, we present LLAP, a hand tracking system that uses ultrasound to localize the hand of the user to enable device-free gesture inputs. LLAP utilizes speakers and microphones on Commercial-Off-The-Shelf (COTS) mobile devices to play and record sound waves that are inaudible to humans. By measuring the phase of the sound signal reflected by the hands or fingers of the user, we can accurately measure the gesture movements. With a single pair of speaker/microphone, LLAP can track hand movement with accuracy of 3.5 mm. For devices with two microphones, LLAP enables drawing-in-the air capability with tracking accuracy of 4.6 mm. Moreover, the latency for LLAP is smaller than 15 ms for both the Android and the iOS platforms so that LLAP can be used for real-time applications.