The increasing processing demands of today's mobile deep learning applications impose stringent requirements on edge devices. Offloading these tasks to the cloud, while being a potential solution, often results in significant data transfer overhead, as well as privacy and connectivity concerns. To address these challenges, split machine learning (split ML) has emerged as an innovative paradigm, enabling task distribution among edge devices themselves. However, split ML systems inherently exhibit instability due to the hardware and communication limitations of mobile devices, which frequently result in failures and malfunctions of client nodes. In light of these challenges, we present Axolotl, a fault-tolerant edge split ML inference system for addressing node failure with minimal performance impact. Specifically, we first design a novel curriculum dropout mechanism to enhance the model's resilience by gradually exposing it to potential server node failures. We then design inverse-proximal weight consolidation to mitigate catastrophic forgetting caused by curriculum dropout. To further tackle potential node failures, we innovate in a resource-aware substitution module that offload the functions of a failed node to neighboring ones, ensuring efficient information flow. Extensive experiments demonstrate the effectiveness and robustness of Axolotl in various deep learning networks and tasks in edge environments.

Radio-Frequency (RF)-based Human Activity Recognition (HAR) rises as a promising solution when low-light, obstructions, or privacy concerns render computer vision impractical. However, thescarcityof labeled RF data due to their non-interpretable nature poses a significant obstacle. Thanks to the recent breakthrough offoundation models (FMs), extracting deep semantic insights from unlabeled visual data become viable, yet these vision-based FMs fall short when applied to small RF datasets. To bridge this gap, we introduce FM-Fi 2.0, an innovative cross-modal framework engineered to translate the knowledge of vision-based FMs for enhancing RF-based, multi-person HAR systems. FM-Fi 2.0 first employs the intrinsic capabilities of FM and RF modality to associate both intra- and cross-modal features of each subject, while simultaneously filtering out irrelevant features to achieve better alignment between the two modalities. FM-Fi 2.0 also employs a cross-modalcontrastiveknowledge distillation mechanism, enabling an RF encoder to inherit the interpretative power of FMs for achieving zero-shot learning. The framework is further refined through metric-based few-shot learning techniques, aiming to boost the performance for predefined HAR tasks. Comprehensive evaluations evidently indicate that FM-Fi 2.0 rivals the effectiveness of vision-based methodologies, and the evaluation results provide empirical validation of FM-Fi 2.0's generalizability across various environments.

Leveraging direct-to-cell (DTC) satellites in low-earth orbits (LEO) to directly provide communication services for terrestrial cellphones is gaining popularity in recent years. However, the unique characteristics of the wireless medium in space-ground communication, combined with the dynamic behavior of LEO satellites, raise a new privacy leakage risk that an adversary eavesdropping on DTC broadcasts could steal the physical locations of active users. In this paper, we investigate new techniques to analyze the location leakage risks in emerging LEO direct-to-cell satellite networks (DCSN). We present DCATOR1DCATOR indicates the abbreviation of DCSN terminal locator. , a novel location leakage analyzer which continuously monitors DTC signaling messages in broadcast channels, extracts various location clues and combines them with the time-varying satellite trajectories to infer the physical locations of active users. We use DCATOR to analyze the consequences if an adversary is able to continuously monitor and process broadcast DTC signaling to deduce the locations of other users within the same satellite coverage area, in three representative DCSNs: (i) the operational Iridium; (ii) the developing Starlink DTC; and (iii) a DCSN based on the latest 3GPP NTN standards. Our extensive experiments demonstrate the existence of location leakages in real DCSNs, and in the worst case an adversary can precisely track the locations of other users within hundreds of meters. Finally, we propose privacy-enhancing countermeasures for DCSNs.

Radio-Frequency (RF)-based Human Activity Recognition (HAR) rises as a promising solution for applications unamenable to techniques requiring computer visions. However, the scarcity of labeled RF data due to their non-interpretable nature poses a significant obstacle. Thanks to the recent breakthrough of foundation models (FMs), extracting deep semantic insights from unlabeled visual data become viable, yet these vision-based FMs fall short when applied to small RF datasets. To bridge this gap, we introduce FM-Fi, an innovative cross-modal framework engineered to translate the knowledge of vision-based FMs for enhancing RF-based HAR systems. FM-Fi involves a novel cross-modal contrastive knowledge distillation mechanism, enabling an RF encoder to inherit the interpretative power of FMs for achieving zero-shot learning. It also employs the intrinsic capabilities of FM and RF to remove extraneous features for better alignment between the two modalities. The framework is further refined through metric-based few-shot learning techniques, aiming to boost the performance for predefined HAR tasks. Comprehensive evaluations evidently indicate that FM-Fi rivals the effectiveness of vision-based methodologies, and the evaluation results provide empirical validation of FM-Fi's generalizability across various environments.