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.

Modern cloud applications, from interative web services to mobile and WoT workloads, generate highly dynamic multi-tenant network demands. Guaranteeing priority-aware bandwidth remains challenging: legacy shapers like Linux Traffic Control Hierarchical Token Bucket are static and unscalable, while cloud-native solutions such as Cilium offer only coarse-grained rate limiting. We present BeeQoS, a cloud-native QoS system that delivers low-latency, adaptive, and scalable multi-priority bandwidth guarantees. BeeQoS consists of an eBPF-powered data plane for high-performance, fine-grained per-packet shaping, a demand-aware control plane that senses real-time flow requirements and adaptively reallocates bandwidth, and seamless Kubernetes integration for expressive policy specification and cluster-wide scalable deployment. Evaluation shows that BeeQoS scales to 1K+ flows with stable performance, boosts high-/medium-priority throughput by 14.6%/36.4%, cuts median latency by 72.4%, reduces deployment overhead, and improves video QoE by 27.3% over state-of-practice baselines.

While existing far memory and disaggregated memory solutions provide a foundation for addressing limitations of single-node memory capacity and inefficient resource allocation in data centers, they predominantly focus on host memory, overlooking the critical demands of GPU-centric workloads. A key bottleneck in scaling GPU memory is the lack of connectivity and interoperability between GPUs, which is exacerbated by their heterogeneity. To bridge this gap, this paper proposes UHM, a unified data transferring and memory pooling scheme for heterogeneous GPU memories. UHM establishes the communication channels between heterogeneous GPU/host memories and leverages double data buffers for pipelined and reliable transfer. Furthermore, UHM unifies both local and remote memories to build a memory pool. The pooling scheme effectively integrates local and remote resources, performs efficient caching management in local memory, and optimizes memory block management for remote memory resources. Evaluation on a heterogeneous GPU cluster demonstrates that UHM significantly reduces the data transfer latency (up to 87.2%), improves the cache hit ratio, reduces runtime memory allocation latency (up to 94.7%), while enhancing the overall memory utilization (24.7%).

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.

With the rapid development of the Industrial Internet of Things (IIoT), the industrial wireless sensor network (IWSN) with strong information perception capability and strict service quality requirements has been derived. The robust operation of the network plays a crucial role in the collection and transmission of important industrial information. Therefore, it is imperative to solve the problems of short network life and low Quality of Service (QoS). Considering these problems, this article comprehensively considers the energy consumption, remaining energy, packet loss rate, and delay, and designs a new multiobjective clustering model to accurately and reasonably elect cluster heads. Based on the advantages of the model, a novel multiobjective high-performance clustering framework (namely, MHCF-CECSO) is proposed to improve the overall performance of IWSN. Specifically, in MHCF-CECSO, a novel chaotic multilevel elite clone snake optimization method is designed to enhance the optimal clustering mechanism. To further improve the clustering efficiency of MHCF-CECSO, chaos optimization is designed to perform an initial search for the snake group to enhance the diversity of the snake group and the algorithm’s ability to escape from local optimum. In addition, a new multilevel elite cloning strategy is designed, which effectively improves the convergence speed of MHCF-CECSO. Comparing experiments with three state-of-the-art clustering schemes are conducted in four different scenarios, and the results show that the proposed MHCF-CECSO outperforms the other three comparison schemes in terms of network lifetime, energy consumption control, and reliability.

Underwater acoustic sensor network (UASN) is a highly practical and popular sensor network extensively utilized for marine environmental monitoring and underwater exploration. Due to the high frequency of node usage, limited energy resources and high QoS performance requirements in UASN, it is necessary to adopt a comprehensive and integrated routing algorithm. In this paper, an innovative comprehensive clustering routing model is designed to accurately reflect the practical usage of UASN. Furthermore, a novel clustering routing algorithm, namely multi-objective differential chaotic shuffled frog leaping algorithm (MDCSFLA), is proposed. This algorithm effectively extends the network lifetime, greatly optimizes network energy balance, and improves network QoS performance. Additionally, by designing a novel differential local search strategy and chaotic perturbation strategy, the global optimization capability is significantly enhanced, and the convergence speed of the algorithm is effectively improved. Through a series of experiments, it is demonstrated that compared to LEACH-C, Q-LEACH, OptGACHE, and UCPSO, the proposed approach demonstrates a significant improvement in network lifetime and throughput, with an increase of at least 22.70% and 27.51%, respectively. Additionally, it achieves substantial reductions of at least 5.92% in average data transmission latency and 16.04% in packet loss rate.

The wireless sensor network (WSN) profoundly impacts the routing technology of the Internet of Things, which has received tremendous attention in terms of energy cost, quality of service (QoS) and security. In this way, it is particularly significant to find a multi-hop path with low energy consumption, delay, delay jitter, packet loss rate and high bandwidth, credibility in WSN. However, the existing energy-efficient secure QoS routing problem has been proven to be an NP-hard that forces a trade-off between energy cost, communication quality and security. To address this problem, a new energy-efficient secure QoS routing model is designed, which precisely replicates the communication scenario of WSN and comprehensively considers energy cost, latency, delay jitter, bandwidth, credibility, and packet loss rate. Subsequently, a novel energy-efficient secure QoS routing algorithm based on elite niche clonal evolutionary computing (ESQRA-ENCEC) is proposed, which includes three novel operators named niche selection, clone operator and elite optimization. These operators are designed to significantly increase the quality of solutions, vigorously develop convergence speed and successfully avoid local optima. The suggested algorithm not only considerably lowers energy consumption, delay, delay jitter and packet loss rate, but also effectively increases bandwidth and credibility. The simulation of ESQRA-ENCEC is performed in different scenarios. Experiment results reveal that the ESQRA-ENCEC has improved by 5.21%, 11.26% in energy cost, 5.31%, 7.94% in bandwidth, 6.44%, 10.80% in delay, 5.85%, 12.79% in delay jitter, 8.58% 14.39% in packet loss rate and 8.03%, 15.58% in credibility compared with two existing algorithms, respectively.

With the widespread application of the Industrial Internet of Things (IIoT), the requirements for sensing equipment to collect data and information continue to increase, and industrial wireless sensor networks (IWSNs) with industrial information perception capabilities have emerged as the times require. The data stream transmission of important value information requires the network to provide safe and reliable service quality assurance. Therefore, it is imperative to meet the requirements of end-to-end delay and reliable service between nodes and solve the problems of high energy consumption and poor security of the existing Quality-of-Service (QoS) routing protocols. To this end, considering the QoS constraints of end-to-end delay, security, and energy consumption, a multiobjective secure routing model based on trust awareness is designed. Subsequently, using the advantages of the proposed model, a novel QoS-secure routing algorithm based on multiobjective chaotic elite adaptive ant colony optimization (ACO) (i.e., MCEAACO-QSRP) is proposed. Specifically, a chaotic optimization strategy is designed to initialize the population, which increases the diversity of the population and enhances the ability of the algorithm to jump out of the local optimal. In addition, the adaptive optimization strategy is designed to dynamically adjust the algorithm trend, which effectively improves the algorithm convergence speed. The performance of the proposed algorithm is evaluated in different scale scenarios. The simulation results show that compared with other state-of-the-art QoS routing solutions, the proposed MCEAACO-QSRP has obvious advantages, which can effectively improve routing security, reduce network energy consumption, and satisfy multi-QoS constrains for the end-to-end delay and reliable service.

Compared with conventional wireless sensor networks (WSNs), industrial WSNs (IWSNs) have stricter requirements in real-time data transmission, energy consumption, and energy uniformity. To fulfill these requirements, a new energy-efficient clustering approach using quantum-related bioinspired optimization, i.e., quantum elite gray wolf optimization (QEGWO), is proposed to improve the performance of IWSNs. Innovatively, a new quantum operator, including quantum probability amplitude, quantum rotation gate, and quantum NOT gate, is designed in QEGWO to enhance its global search capability. This quantum operator need not query the quantum rotation angle table in updating quantum probability amplitude with the quantum rotation gate, which reduces the computational complexity of introducing quantum optimization into the clustering problem of IWSNs. Moreover, to enhance the convergence performance of the clustering algorithm, a multielite strategy is proposed to preserve the historical optimal individuals generated in the iterative process by establishing a dynamic elite pool. Compared with the state-of-the-art clustering approaches, extensive simulations in four different scenarios are carried out, and the results demonstrate that the proposed QEGWO outperforms other comparison approaches in delay, energy consumption, and energy uniformity.