Multi-participant meetings occur across various domains, such as business negotiations and medical consultations, during which sensitive information like trade secrets, business strategies, and patient conditions is often discussed. Previous research has demonstrated that attackers with mmWave radars outside the room can overhear meeting content by detecting minute speech-induced vibrations on objects. However, these eavesdropping attacks cannot differentiate which speech content comes from which person in a multi-participant meeting, leading to potential misunderstandings and poor decision-making. In this paper, we answer the question ``who speaks what''. By leveraging the spatial diversity introduced by ubiquitous objects, we propose an attack system that enables attackers to remotely eavesdrop on in-person conversations without requiring prior knowledge, such as identities, the number of participants, or seating arrangements. Since participants in in-person meetings are typically seated at different locations, their speech induces distinct vibration patterns on nearby objects. To exploit this, we design a noise-robust unsupervised approach for distinguishing participants by detecting speech-induced vibration differences in the frequency domain. Meanwhile, a deep learning-based framework is explored to combine signals from objects for speech quality enhancement. We validate the proof-of-concept attack on speech classification and signal enhancement through extensive experiments. The experimental results show that our attack can achieve the speech classification accuracy of up to $0.99$ with several participants in a meeting room. Meanwhile, our attack demonstrates consistent speech quality enhancement across all real-world scenarios, including different distances between the radar and the objects.

Jinheng Wang, Hansong Zhou, Ting Song, Shijie Cao, Yan Xia, Ting Cao, Jianyu Wei, Shuming Ma, Hongyu Wang, Furu Wei. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Speaker diarization refers to identifying who speaks what in a conversation. It is critical in sensitive settings like psychological counseling and legal consultations. However, traditional approaches, such as microphone or video, raise privacy concerns and cause discomfort to participants due to their noticeable deployment. To address this, we propose a non-intrusive speaker diarization system via mmWave sensing. Our approach leverages the spatial diversity of signals from multiple objects to distinguish speakers. Specifically, it isolates speech-induced vibrating objects signals and extracts speaker-related features through a two-stage feature extraction process. Our system achieves over 93% accuracy in real-world scenarios, demonstrating its effectiveness in reliably distinguishing speakers.

Future mobile edge computing (MEC) is envisioned to provide federated intelligence to delay-sensitive learning tasks with multimodal data. Conventional horizontal federated learning (FL) suffers from high resource demand in response to complicated multi-modal models. Multi-modal FL (MFL), on the other hand, offers a more efficient approach for learning from multi-modal data. In MFL, the entire multi-modal model is split into several sub-models with each tailored to a specific data modality and trained on a designated edge. As sub-models are considerably smaller than the multi-modal model, MFL requires fewer computation resources and reduces communication time. Nevertheless, deploying MFL over MEC faces the challenges of device mobility and edge heterogeneity, which, if not addressed, could negatively impact MFL performance. In this paper, we investigate an Service Migration-assisted Mobile Multi-modal Federated Learning (SM3FL) framework, where the service migration for sub-models between edges is enabled. To effectively utilize both communication and computation resources without extravagance in SM3FL, we develop the optimal strategies of service migration and data sample collection to minimize the wall-clock time, defined as the required training time to reach the learning target. Our experiment results show that the proposed SM3FL framework demonstrates remarkable performance, surpassing other state-of-art FL frameworks via substantially reducing the computing demand by 17.5% and dramatically decreasing the wall-clock time by 25.3%.

Internet of Things (IoT) is transforming every corner of our daily life and plays important roles in the smart home. Depending on different requirements on wireless transmission, dedicated wireless protocols have been adopted on various types of IoT devices. Recent advances in Cross-Technology Communication (CTC) enable direct communication across those wireless protocols, which will greatly improve the spectrum utilization efficiency. However, it incurs serious security concerns on heterogeneous IoT devices. In this paper, we identify a new physical-layer attack, cross-technology signal emulation attack, where a WiFi device eavesdrops a ZigBee packet on the fly, and further manipulates the ZigBee device by emulating a ZigBee signal. To defend against this attack, we propose two defense strategies with the help of a commonly found WiFi router. Particularly, the passive defense strategy focuses on misleading the ZigBee signal eavesdropping, while the proactive approach develops a real-time detection mechanism on distinguishing between a common ZigBee signal and an emulated signal. We implement the complete attacking process and defense strategies with TI CC26x2R LaunchPad, USRP-N210 platform, and a self-designed prototype. Extensive experiments have demonstrated the existence of the attack, and the feasibility, effectiveness, and accuracy of the proposed defense strategies.