Embedded system development is crucial for enabling seamless connectivity and functionality across a wide range of Internet of Things (IoT) applications. However, such a complex process requires cross-domain knowledge of hardware and software and hence often necessitates direct developer involvement, making it labor-intensive, time-consuming, and error-prone. To address this challenge, this paper introduces AutoEmbed, the first automated software development platform for general-purpose embedded IoT systems. The key idea is to leverage the reasoning ability of Large Language Models (LLMs) and embedded system expertise to automate the hardware-in-the-loop development process. The main methods include a component-aware library resolution method for addressing hardware dependencies, a library knowledge generation method that injects utility domain knowledge into LLMs, and an auto-programming method that ensures successful deployment. We evaluate AutoEmbed’s performance across 71 modules and four mainstream embedded development platforms with over 350 IoT tasks. Experimental results show that AutoEmbed can generate codes with an accuracy of 95.7% and complete tasks with a success rate of 86.5%, surpassing human-in-the-loop baselines by 15.6%–37.7% and 25.5%–53.4%, respectively. We also show AutoEmbed ’s potential through case studies in environmental monitoring and remote control systems development. © 2026 Copyright held by the owner/author(s).

The rapid proliferation of emotion-aware web services has necessitated the analysis of multimodal user interactions. However, this introduces new vulnerabilities where adversaries exploit emotional signals to circumvent fraud detection systems. Despite its improved utility, the robustness of multimodal fraud detection against emotion-driven adversarial manipulation remains significantly underexplored. Existing paradigms often treat emotional cues as static features, overlooking the adversary's capability to strategically modulate multimodal signals (e.g., facial micro-expressions, vocal intonation, and textual styles) to mimic genuine behavior. Furthermore, prevalent evaluations are typically confined to unimodal perturbations and fail to account for context-consistent, cross-modal attacks, thereby compromising system reliability in real-world deployments. To bridge this gap, we propose Context-Emotion Adversarial Training (CEAT), a robust framework designed to fortify multimodal fraud detection against emotion-based attacks. CEAT leverages a Transformer-based architecture to synergistically model emotional features (e.g., visual dynamics and acoustic prosody) alongside semantic context derived from text, yielding a unified representation. Crucially, CEAT introduces a context-aware perturbation mechanism that injects noise into the emotional latent space during training. This process preserves semantic consistency while encouraging the learning of emotion-invariant and discriminative representations. Additionally, a contrastive learning objective is integrated to maximize the distributional divergence between genuine and adversarial samples within the latent manifold. Extensive experiments on multimodal benchmarks demonstrate that CEAT significantly outperforms state-of-the-art baselines, exhibiting superior robustness under simulated emotion-driven attack scenarios.

Deep learning has significantly advanced Radio Frequency (RF) sensing, leading to extensive research and practical applications in both academia and industry. However, these advancements have also introduced potential privacy and security threats to RF sensing data. In this paper, we present RFInv, the first model inversion attack targeting deep learning classifier-empowered RF sensing systems. RFInv can recover users' private sensing data without knowledge of the RF sensing model's structure, relying solely on the output prediction vector of the deep learning classifier. Consequently, this recovered sensitive data can be exploited for malicious purposes such as identity impersonation and unauthorized device control. To realize the proposed attack, we develop a deep generative adversarial network that integrates an inversion module and a critic module, enabling effective RF data recovery in black-box scenarios. To address the unique challenge of preserving physical consistency in RF data, we incorporate attention mechanisms and deformable convolutions to model their complex temporal and spatial dynamics, ensuring physical consistency. Furthermore, a spectrogram alignment loss is introduced to further enhance reconstruction accuracy. The network is trained using an auxiliary dataset, circumventing the need for access to the target model's training data. We systematically evaluate our proposed attack across multiple datasets for various RF sensing tasks and target models with different network architectures. Extensive experiments demonstrate that RFInv can recover diverse types of RF privacy data with an average Structural Similarity Index Measure (SSIM) of 0.78 and achieves an 86.21% Relative Attack Success Rate (RASR).

Mobile Edge Computing (MEC) utilizes edge servers to offload the computational burden from cloud infrastructure. By providing low-latency and high-bandwidth services, MEC enables mobile users and IoT devices to efficiently offload and execute computational tasks at the network edge. However, optimizing communication and computational resources in a multi-user, multi-server MEC environment remains a significant challenge. In this paper, we propose TSAJS, an efficient multi-server joint task scheduling scheme designed to enhance the effectiveness of MEC offloading. We model the task offloading and resource allocation problem as a Mixed-Integer Nonlinear Programming (MINLP) problem, aiming to maximize user offloading gain by minimizing task completion time and energy consumption. A heuristic algorithm for offloading is introduced by combining threshold-triggering and simulated annealing to effectively avoid local optima and converge toward the global optimum. Meanwhile, the optimal solution for resource allocation is derived using the Karush-Kuhn-Tucker (KKT) conditions. Experimental results demonstrate that TSAJS delivers near-optimal performance, outperforming traditional methods in terms of user offloading effectiveness. Its efficiency enables solution finding within polynomial time, while also adapting to the preferences of users and service providers.

Audio recognition systems have become integral to various applications, including speech-to-text, virtual assistants, and security monitoring, where efficiency and privacy are key concerns. The collaborative recognition system (CRS) partitions and deploys the neural network (NN) across multiple edge devices for cooperative recognition without sharing raw audio data. This distributed approach significantly alleviates the computational burden on the client and ensures data privacy. These advantages make CRS increasingly prevalent in audio recognition applications to improve security, efficiency, and provide timely feedback. However, sharing information during collaboration still poses the risk of exposing original data. To the best of our knowledge, this paper introduces InverCRS, the first inversion attack targeting CRS-empowered audio recognition systems. InverCRS is a generative attack in which the attacker trains a local generative model to take intermediate results as input and output the original audio. Once the generative model is trained, it can perform audio inversion using new intermediate results without the need for further optimization. Furthermore, InverCRS utilizes heuristic algorithms to approximate gradients, making it applicable to both white-box and black-box scenarios. We conduct comprehensive experiments to evaluate the feasibility and efficiency of InverCRS across two real-world audio datasets. The results demonstrate that InverCRS can effectively reconstruct the original audio from various split points within the CRS. Additionally, we investigate two potential defense strategies and provide experimental evaluations of their effectiveness in mitigating this attack.

Gait-based authentication has risen to prominence for its distinctive advantages, becoming an essential security mechanism for mobile devices. These devices typically employ Inertial Measurement Units (IMUs) to capture intricate gait patterns for confirming the identity of users. However, our research highlights a vulnerability: the user’s gait data on mobile devices is susceptible to interception through a radio frequency (RF) side-channel, potentially allowing unauthorized access. We introduce Gait-Snoop as aproof-of-concept for this novel side-channel attack. Gait-Snoop utilizes the RF signals reflected during a user’s walk to extract gait information. It then correlates these RF signal patterns with IMU-derived gait data and employs a robotic arm to replicate the gait, aiming to deceive and unlock the targeted mobile devices. Our comprehensive evaluation of Gait-Snoop on smartphones demonstrates its capability to mimic IMU gait signals, underscoring the effectiveness and potential risks of such side-channel attacks.

Diverse Wi-Fi-based wireless applications have been proposed, ranging from daily activity recognition to vital sign monitoring. Despite their remarkable sensing accuracy, the high energy consumption and the requirement for customized hardware modification hinder the wide deployment of the existing sensing solutions. In this paper, we propose REHSense, an energy-efficient wireless sensing solution based on Radio-Frequency (RF) energy harvesting. Instead of relying on a power-hungry Wi-Fi receiver, REHSense leverages an RF energy harvester as the sensor and utilizes the voltage signals harvested from the ambient Wi-Fi signals to enable simultaneous context sensing and energy harvesting. We design and implement REHSense using a commercial-off-the-shelf (COTS) RF energy harvester. Extensive evaluation of three fine-grained wireless sensing tasks (i.e., respiration monitoring, human activity recognition, and hand gesture recognition) shows that REHSense can achieve comparable sensing accuracy with conventional Wi-Fi-based solutions while adapting to different sensing environments, reducing the power consumption of sensing by 98.7% and harvesting up to 4.5 mW of power from RF energy.

Video surveillance systems play a crucial role in ensuring public safety and security by capturing and monitoring critical events in various areas. However, traditional surveillance cameras face limitations when it comes to malicious physical damage or obscuring by offenders. To overcome this limitation, we proposem$^{2}$2Vision, which is the first millimeter-wave (mmWave)-based video reconstruction system designed to enhance existing video surveillance cameras.m$^{2}$2Visionutilizes mmWave to sense the profile and motion signature of the target, integrating it with previously acquired visual data about the environment and the target's appearance, thereby facilitating the reconstruction of surveillance video. Specifically, our proposed system incorporates a dual-stage mmWave signal denoising algorithm to efficiently eliminate the noise and multiple-input multiple-output virtual antenna enhanced heatmap generation (MVAE-HG) method to obtain fine-grained mmWave heatmaps responsive to the target's profile and motion information. Moreover, we design the mm2Video generative network that first employs a multi-modal fusion module to fuse the mmWave and pre-acquired visual data, then use a conditional generative adversarial network (cGAN)-based video reconstruction module for surveillance video reconstruction. We conducted comprehensive experiments onm$^{2}$2Visionusing a commercial mmWave radar and four surveillance cameras across various environments, with the participation of seven individuals. Evaluation results show thatm$^{2}$2Visioncan achieve an average structural similarity index measure (SSIM) of 0.93, demonstrating its effectiveness and potential.

Handwritten signature verification has become one of the most important document authentication methods that are widely used in the financial, legal, and administrative sectors. Compared with offline methods based on static signature images, online handwritten signature verification methods are more reliable because of the temporary dynamic information (e.g., signing velocity, writing force, stroke order) that alleviates the risk of being forged. However, most existing online handwritten signature verification solutions are reliant on specific signing devices (e.g., customized pens or writing pads) and require extensive data collection during the registration phase, resulting in poor adaptability and applicability for new users. In this article, we propose mmSign, a millimeter wave (mmWave)–based online handwritten signature verification system, which enables accurate sensing of the user’s hand movements when signing through the superior sensing capability of mmWave. mmSign extracts the time-velocity feature maps from the captured mmWave signals by the carefully designed signal processing algorithms and then exploits a transformer-based verification model for signature verification. In addition, a novel meta-learning strategy with proposed task generation and data augmentation methods is introduced in mmSign to teach the verification model to learn effectively with limited samples, allowing our model to quickly adapt to new users. Extensive experiments show that mmSign is a robust, efficient, and secure handwritten signature verification system, achieving 84.07%, 87.31%, 91.12%, and 96.54% verification accuracy when 1, 3, 5, and 10 labeled signatures are available, respectively, while being resistant to common forgery attacks.

In recent years, the deployment of unmanned vehicle delivery services has increased unprecedentedly, leading to a need for enhanced security due to the risk of leaving high-value packages to an unauthorized third party during pickup or delivery. Existing authentication methods such as QR code and one-time password are inadequate, as they are susceptible to attacks and provide only one-way authentication. This paper, for the first time to our best knowledge, proposes Wave-for-Safe (W4S) --- a novel mutual authentication system that utilizes multi-modal sensors on both the user's smartphone and the unmanned vehicle. W4S uses random hand-waving by the legitimate user to achieve robust authentication by obtaining highly correlated sensory data measured by the Inertial Measurement Unit (IMU) in the smartphone and sensors in the unmanned vehicle (e.g., mmWave radar and camera). We propose several novel methods to overcome challenges such as heterogeneous data processing, asynchronization, and imitating attacks. The prototype is implemented on an unmanned vehicle and various smartphones, and evaluation in different real-world scenarios shows that W4S achieves an equal error rate below 0.013 against various attacks.

Radio Frequency (RF)-based gait recognition has emerged as a promising technology to authenticate individuals in a pervasive and unobtrusive way. However, a fundamental challenge remains in collecting extensive data of the same user in the same environment. To address this challenge, this paper introduces XGait, a cross-modal gait recognition framework that does not require the prior deployment of RF devices or explicit data collection. The key idea is to leverage the signals of the Inertial Measurement Unit (IMU), which is widely available in modern mobile devices, to simulate the RF signals that would be generated if the same person walked near RF devices. Despite the straightforward idea, several technical challenges need to be addressed due to the diversity of RF devices, the intrinsic difference between IMU signals and RF signals, and the complexity of gait. First, we propose an RF spectrogram generation method to consistently extract essential RF gait data features across different RF signals. Secondly, we propose a generative network-enabled IMU-to-RF translation approach that accurately converts IMU data to RF data. Finally, we design an RF gait spectrogram-specific transformer model to further improve the recognition performance. We conduct a comprehensive evaluation of XGait, involving thirty subjects in three different environments, utilizing three RF devices and seven mobile devices. Experimental results show that XGait consistently achieves over 99% Top-3 accuracy in various scenarios.

From the perspective of privacy protection and convenience, WiFi-based person identification in wireless sensing has attracted extensive attention in recent years. In this paper, we propose a WiFi-based person IDentification (WiID) method, which can capture people’s valid physiological information from Channel State Information (CSI) of different spatial streams even when people are in motion. The key idea is to detect and extract the short-time static states from the collected CSI and achieve person identification based on these short-time signals. By designing a Motion Sensitivity Vector (MSV) conversion algorithm, WiID is able to segment CSI that carries individual physiological information automatically without the individual performing an assigned action or maintaining a specific state. As far as we know, it is the first work that enables precise person identification using people’s physiological information when people do not keep stationary. Experimental results in real-life scenarios show that WiID can achieve 92.65% of average accuracy in three different environments.