Collaborative Edge Computing (CEC) enables effective load balancing by decomposing tasks across edge servers. However, due to limited computing and storage resources in CEC networks, eliminating computational redundancies becomes particularly important for improving overall efficiency and conserving resources. To address this, we propose a novel compute-storage cooperation framework that jointly optimizes task offloading and computation result caching to minimize system-wide delay and caching cost. The optimization problem is decomposed into two subproblems: reusable task scheduling and reusable data caching. Accordingly, the CoRe-S algorithm and the VaRe-C algorithm along with a proactive pre-caching mechanism are proposed to solve these subproblems, respectively. By leveraging temporal and spatial correlations among computational tasks, the proposed framework directly caches computation results to reduce redundant processing. In addition, the age of data is incorporated into the evaluation metric to better assess the value of cached results, thereby enhancing reuse efficiency. Theoretical analysis and extensive simulations are conducted to validate the effectiveness and superiority of the proposed algorithms. Compared with state-of-the-art baselines, our method reduces the total cost by up to 41.89% and achieves a cache hit rate of 53.1%.

Trusted execution environments (TEEs), like TrustZone, are pervasively employed to protect security sensitive programs and data from various attacks issued by untrusted rich execution environments (REEs) while they execute compact TEE operating systems which implement minimum security-critical operations but have poor device driver support. In this paper, we propose a twin driver approach where a pair of TEE and REE drivers is generated and cooperate to enable secure and efficient TEE driver support. To begin with, we propose a driver data flow analysis framework named driver analyzer (DrvAna) to automatically analyze the shared states between the TEE and REE driver where a novel data structure named value-type tree is investigated to facilitate field-sensitive data flow analysis upon the driver state. Furthermore, in order to maintain a minimal trusted computing base, we propose a Linux driver runtime (LDR) inside the TEE, a sandbox environment that confines the TEE driver based on the ARM domain access control features and mediates the driver's interaction with the TEE. We implement a DrvAna prototype based on LLVM as well as an LDR prototype on an NXP IMX6Q SABRE-SD evaluation board, adapt 6 existing Linux drivers into LDR, and evaluate their performance. The experimental results show that the LDR drivers can achieve comparable performance with their Linux counterparts with negligible overheads.

Indoor localization and trajectory tracking in multi-story, energy-constrained IoT environments such as smart healthcare and industrial monitoring remain challenging. This paper investigates how to achieve reliable, fine-grained localization under practical cost and power constraints that necessitate single-gateway LoRa deployments. Existing methods such as Wi-Fi, BLE, and UWB require dense infrastructure or incur high power consumption, while conventional RSSI fingerprinting lacks robustness and cross-domain generalization. Generative methods such as GANs and VAEs typically exhibit training instability and produce oversmoothed fingerprints, which limits their applicability to complex indoor environments. To address these gaps, we present D-Trace, a lightweight trajectory tracking system that employs a conditional diffusion model to generate high-fidelity RSSI fingerprints guided by spatial priors. The system introduces an RSSI + feature representation that enhances discriminability and robustness, reduces manual data collection, and enables cross-domain generalization across floors and LoRa configurations. Extensive experiments in a multi-floor building show that D-Trace achieves 95.94% localization precision with a 0.5 m mean error under sparse deployments, and maintains up to 90.3% precision with a 3.26 m average error in cross-domain scenarios. These results validate the system’s practicality, scalability, and robustness for resource-constrained IoT deployments, providing a cost-effective solution for intelligent indoor tracking.

Nowadays, as mobile robots and devices become smaller and lighter, forming them into swarms to collaboratively complete tasks has become an important research area. The previously introduced Ultra-Wideband (UWB) Swarm Ranging (SRv1) protocol pioneered simultaneous data transmission and ranging. However, it suffers from performance degradation in large-scale robot or device swarms.This paper introduces Swarm Ranging 2.0, a fundamentally redesigned and theoretically optimal protocol, which pushes the DS-TWR method to its theoretical limit, maximizing the number of distance calculations. Firstly, we propose a novel compensatory ranging method, enabling additional ranging for dynamic swarms. Next, we analyze the primary packet loss scenarios and redesign the ranging message and ranging table (data structure) to achieve robust ranging. Subsequently, to cope with complex combinations of packet loss and inconsistent frequency, we model the new protocol using a state machine. Theoretical analysis further proves its optimality. We implement the protocol on Crazyflie 2.1 drones equipped with DW3000 UWB transceivers. Experiments with 25 drones show a 47.8% improvement over SRv1 and over 300% improvement compared to standard UWB protocol, demonstrating the protocol’s scalability and effectiveness in real-world swarm deployments. The protocol is open-sourced at https://github.com/SEU-NetSI/crazyflie-firmware.

Industrial Edge Computing (IEC) networks have attracted growing attention, where industrial devices offload computation-intensive and delay-sensitive tasks to edge servers. Task offloading scheduling is fundamental to ensuring quality of service in IEC networks. However, most existing studies assume complete network information, which is difficult or even infeasible to obtain in practical IEC deployments due to dynamic workloads and partial observability. As a result, their performance degrades in IEC networks with incomplete information. To address this issue, this paper proposes a group centric task offloading framework tailored to IEC networks with incomplete information and formulates a delay minimization scheduling problem. For the framework design, we develop the GBG algorithm to obtain the optimal grouping and bandwidth allocation strategy. For online scheduling, the scheduling sub problem is modeled as a Partially Observable Markov Decision Process, and the SGOS algorithm is proposed by integrating Long Short-Term Memory with Soft Actor–Critic to handle incomplete information. Extensive simulations and testbed experiments show that the proposed approach consistently outperforms baseline schemes in convergence speed, delay, and workload balance.

Recently, there has been an emerging radio frequency fingerprint identification (RFFI) technology that enhances fingerprint distinguishability by deliberately injecting an RF fingerprint into the device's Wi-Fi baseband signal. The current RF fingerprint injection methods are impractical, degrading the communication quality between Wi-Fi devices while offering limited improvements in distinguishability among a set of devices. To address these issues, we propose injecting I/Q imbalance into a short training field (STF) instead of the entire baseband signal. Our findings indicate that this method can effectively preserve the quality of the original wireless communication. Besides, a temperature-independent RF feature differential carrier frequency offset (DCFO) is proposed as an extended feature for the enhancement of fingerprint distinguishability. Building upon these, we introduce a fingerprinting scheme called PR-RFFI that generates distinguishable fingerprints for a set of devices by injecting appropriate I/Q imbalance and DCFO into the STF. Leveraging the short-term invariance of the channel, we design a practical I/Q imbalance extraction method based on the communication-quality preserving injection. Moreover, we design an optimal assignment method for I/Q imbalance and DCFO to maximize the distinguishability of RF fingerprints for all devices. Finally, we implement the PR-RFFI solution and conduct experiments in real-world and simulation scenarios. The experimental results demonstrate that PR-RFFI consistently maintains good communication quality, and achieves over 98% precision, recall, and F1-score.

Unmanned Aerial Vehicles (UAVs) are crucial for deadline-driven tasks but face dual bottlenecks: limited flight endurance and constrained onboard processing for data-intensive tasks. Edge Intelligent Vehicles (EIVs) can effectively serve as mobile logistical and computational hubs to alleviate these issues. However, existing research on such air-ground collaboration often assumes predetermined EIV locations and a fixed UAV fleet. This inflexibility leads to costly resource over-provisioning or mission failures under tight deadlines. Motivated by this, this paper studies the SLIM+ problem, which focuses on jointly optimizing proactive EIV placements and UAV fleet sizing to minimize total deployment cost. This problem is challenging due to the deep coupling between strategic EIV placement, which shapes the mission structure, and the resulting operational cost of the UAV fleet. Therefore, we propose a novel two-level algorithm, where the outer layer employs dynamic programming to strategically place EIVs to partition the mission into independent route segments, while the inner layer consists of two complementary algorithms to determine the minimum UAV fleet size and optimal speeds for each segment: an optimal DP-based method and an approximation algorithm with a theoretical guarantee. Extensive simulations show that our integrated solution reduces total deployment cost by an average of 21.9% compared to baseline solutions, highlighting the benefits of a fully optimized co-deployment strategy.

Serverless functions run event-driven code on demand without long-lived servers, which makes them a good fit for dynamic, latency-sensitive edge workloads. However, when a function is invoked for the first time or after idling, the platform must initialize a container and load runtimes and libraries, incurring a cold start delay that can reach hundreds of milliseconds to seconds. The effect is amplified by resource-constrained, bursty edge environments. Existing mitigations include container reuse, prewarming, and fixed retention. These methods help, but still suffer from limited reuse across functions, largely static strategies, and costly real-time decisions. To address these challenges, we propose a layered container framework called Feedback-Aware Hierarchical Edge Scheduler ,(FAHES). It uses Zygote containers to share dependencies across functions and supports dynamic warm pool management, significantly reducing startup latency and memory overhead. To enable dynamic container resource allocation for real-time scheduling, FAHES employs Hidden Markov Models (HMMs) to predict short-term function invocations. FAHES further integrates adversarial and stochastic algorithms to capture system dynamics and make efficient scheduling decisions. We prove that FAHES achieves sublinear regret in scheduling performance. Simulation-based experiments on an edge cluster show that FAHES reduces the overall cost by up to 60.5% compared to state-of-the-art baselines.

In recent years, the Internet of Things (IoT) has rapidly advanced, with applications ranging from smart homes to industrial manufacturing, often involving densely deployed nodes such as temperature and humidity sensors. Since these nodes have limited computation and energy, the use of stuffed Wi-Fi management frames for data transmission has emerged as a promising way to avoid the association overhead of the traditional transmission mode. However, this unassociated data transmission mode continues to encounter significant channel contention in dense deployments. To this end, we propose ODGMAC, an on-demand grouping-based MAC solution that dynamically groups transmission-awaiting nodes and allocates time slots on a per-group basis, thereby enabling intra-group contention to improve transmission efficiency and reduce node energy consumption. Firstly, we present a fuzzy control-based algorithm at the access point (AP) to dynamically identify nodes with transmission demands in the current beacon period. On this basis, we then propose a hierarchical group-based time slot allocation methodology. Specifically, the nodes are initially clustered according to their per-packet airtime requirements. Within each cluster, we evenly partition nodes into multiple groups and assign each group to a unique time slot for channel contention, where the optimal slot count is determined by a renewal-theory-based analytical model with a discrete search over candidate counts. Finally, we implement the ODGMAC testbed with one AP and 100 IoT nodes, and conduct real-world experiments in a dense environment. The experimental results show that our solution outperforms existing methods in terms of both data delivery rate and node power consumption. Specifically, under severe channel collision conditions, our solution achieves an average increase of 14.77% in data delivery rate and an average reduction of 8.21% in node power consumption, while maintaining excellent fairness. Moreover, extended simulations show that our solution scales to 1000 nodes and maintains excellent performance under node mobility.

As the demand for Location-Based Services (LBS) grows in remote or resource-limited regions, providing high Quality of Service (QoS) location for wide mobile applications has become increasingly crucial. Existing approaches typically rely on fixed gateways and static nodes, which is unsuitable or expensive in demanding environments such as wild fields or temporary sites. In this paper, we propose AirLoc, a QoS aware framework that ensures long-range, accurate, and low cost location services for wide mobile scenarios. Considering that LoRa (Long Range) is suitable for localization in wide areas due to its long-range and low-power nature. AirLoc uses only one single legacy UAV-assisted LoRa gateway to track mobile LoRa targets without relying on dense infrastructure. AirLoc is mainly based on the key observation that LoRa's RSSI is insensitive at long ranges and unstable at short ranges. To address these issues, we propose three key service modules for AirLoc framework. We first propose a LoRa spreading factor-based long range localization module to determine the coarse region of the targets. Additionally, we design an RSSI reconstruction–based module to achieve accurate tracking in short ranges. Finally, a QoS-driven interaction protocol module is used to operate the architecture with minimal overhead. We implement AirLoc on both a real-world testbed that includes a UAV-assisted LoRa gateway and a large-scale simulation platform. Extensive real world experiments show that AirLoc accurately tracks mobile targets in a 550 m × 400 m area at low power, making it a QoS-aware, modular service architecture that easily integrates into existing LBS systems.

Recent advances in Large Language Models (LLMs) have revolutionized web applications, enabling intelligent search, recommendation, and assistant services with natural language interfaces. Tool-calling extends LLMs with the ability to interact with external APIs, greatly enhancing their practical utility. While prior research has improved tool-calling performance by adopting traditional computer systems techniques, such as parallel and asynchronous execution, the challenge of redundant or repeated tool-calling requests remains largely unaddressed. Caching is a classic solution to this problem, but applying it to LLM tool-calling introduces new difficulties due to heterogeneous request semantics, dynamic workloads, and varying freshness requirements, which render conventional cache policies ineffective. To address these issues, we propose ToolCaching, an efficient feature-driven and adaptive caching framework for LLM tool-calling systems. ToolCaching systematically integrates semantic and system-level features to evaluate request cacheability and estimate caching value. At its core, the VAAC algorithm integrates bandit-based admission with value-driven, multi-factor eviction, jointly accounting for request frequency, recency, and caching value. Extensive experiments on synthetic and public tool-calling workloads demonstrate that ToolCaching with VAAC achieves up to 11

Pharmaceutical services for traditional Chinese medicine (TCM) are critical to promoting the upgrading of the TCM health service industry. However, the resource representation of these services remains a foundational and key challenge in supporting the digital and intelligent transformation of TCM pharmaceutical services. To address the resource representation problem under the complex characteristics of TCM pharmaceutical service resources, in this study, a resource representation model tailored to TCM pharmaceutical service scenarios is constructed. We then propose a representation method for TCM pharmaceutical service resources based on heterogeneous graph networks (TCM-HGN). By introducing cross-layer semantic coupling and an attention fusion mechanism, TCM-HGN achieves the synergistic expression of complex TCM pharmaceutical business semantics in a unified embedding space. The experiments demonstrate that TCM-HGN significantly outperforms existing benchmark methods across various metrics, achieving a robust representation of multidimensional TCM pharmaceutical service resources.

Federated Learning (FL) enables collaborative model training without exposing private data, but remains vulnerable to backdoor attacks, where malicious clients inject backdoor updates into the global model. Detecting such attacks is challenging due to the noisy and heterogeneous nature of benign updates obscuring backdoor patterns. To this end, we propose Peeler, a lightweight backdoor defense framework that accurately identifies backdoor by dynamically isolating normal model weights orthogonal to malicious ones within client-submitted updates. Peeler employs circuit discovery to prune subnetworks associated with the main task, and utilizes gradient-based layer selection to eliminate layers that are non-critical for backdoor objective adaptation. The remaining parameters are then flattened into feature vectors, enabling distance-based anomaly detection across client-submitted model updates. To validate Peeler, we perform a Neural Tangent Kernel (NTK)-based analysis, showing that Peeler effectively retains backdoor-relevant weights while filtering out benign ones. Experiments across diverse scenarios and recent defense benchmarks demonstrate the superiority of Peeler. Peeler reduces the Attack Success Rate (ASR) to 2.79% on average, significantly outperforming the prior state-of-the-art defense (11.48% for FLAME). Even under highly heterogeneous data distributions (with Dirichlet parameter α = 0.3), Peeler achieves an ASR of 10.4%, compared to the prior state-of-the-art defense (27.3% for FLTracer).

Tor is a widely used network for anonymous communication, employing onion encryption and multi-hop routing to ensure anonymity for its users and service providers. Despite its robust design, Tor has been the target of numerous attacks, such as denial-of-service (DoS) attacks and deanonymization attacks. However, these attacks often rely on resource-intensive methods, such as bandwidth inflation or controlling large-scale nodes. They face limitations due to high costs, limited scalability, and countermeasures that Tor already has in place. In this paper, we identify a new vulnerability, termed the Descriptor Flood, in Tor's memory management mechanism and service publication protocol. By exploiting Descriptor Flood, attackers can flood Tor nodes with malicious descriptors of onion services, causing severe memory fragmentation, exhaustion, and eventual node crash. Unlike conventional attacks, our method leverages a fundamental design flaw, allowing cost-effective and scalable exploitation without requiring substantial resources. To demonstrate the practical impact of this vulnerability, we propose the Tordos Attack, a three-phase strategy that efficiently disables Tor nodes and executes DoS and deanonymization attacks against onion services via tearing down specific nodes in Tor. The attack addresses key challenges, such as measuring node memory capacity, inducing fragmentation, and disabling critical nodes to maximize disruption. Our extensive experimental results indicate that the attack can disable Tor nodes and onion services within 9.1 minutes and expose the onion service's real identity in 6.1 hours, potentially leading to the collapse of the entire Tor network.

Mobile edge computing (MEC) networks have attracted significant attention for enabling users to offload computation-intensive tasks to edge servers. Task offloading scheduling is a critical challenge, especially when complete information about tasks and edge servers is only partially accessible in practice. In general, each edge server can only obtain its own information but has no access to the complete real-time information of other edge servers, resulting in information incompleteness. To address this issue, this article investigates the problem of energy minimization through offloading with incomplete edge information (EMO-IEI). Specifically, to address the uncertainty of real-time computing resources caused by incomplete edge information (IEI), we adopt the exact convex regularization (ECR) method to estimate resource availability based on known expectations and variances. Utilizing these estimations, we reformulate the problem as a collapsing multiknapsack problem and propose the GAP-ESM algorithm for efficient solution. Theoretical analysis validate that the GAP-ESM algorithm achieves an approximation ratio of (1+kappa/(kappa - rho kappa - rho)), where kappa is system parameter associated with the energy requirements of computing tasks, and rho is a tunable design parameter balancing approximation quality and computational complexity. Extensive simulations demonstrate that the proposed GAP-ESM algorithm outperforms baseline schemes in terms of overall energy consumption and task completion rate.

Radio Frequency (RF) wireless power transfer is a novel technique to address the energy hunger problem of modern wireless devices, for which power transfer and data transmission are coordinated by the “harvest-then-transmit” (HTT) protocol. Time-varying RF-powered systems is becoming a research trend and a significant progress has been made recently that proposes an optimal HTT-scheduling algorithm. However, previous research assume the core time-varying charging power function to be continuous, and the battery to be infinitely large, which ease the theoretical analysis. This paper considers a more practical discretely time-varying charging power function and battery overflow caused by limited capacity, and attack an even harder but important problem. We establish a set of optimality properties for the offline problem where the time-varying power transfer is known in advance. Based on these optimality properties, we propose a novel splitting line system, and an optimal iteration-based method to locate the s-lines for the Energy Critical Point (ECP) and Battery Full Point (BFP), respectively and adaptively. Following the optimality principles learned from the offline problem, we design an online heuristic, and its superior performance is demonstrated by simulations.