Edge computing is a promising paradigm that deploys computing resources at the network edge to provide services. Many existing solutions leverage deep reinforcement learning (DRL) to optimize task scheduling, yet they often rely on global scheduling approaches. However, such solutions result in an excessively large decision search space, reducing task scheduling efficiency in complex environments. Additionally, the cold start problem impedes the generation of optimal scheduling strategies. To address these challenges, we propose AEDS, a DRL-based task scheduling framework designed to enhance scheduling efficiency. AEDS optimizes the decision-making process from three aspects: (1)Decision Space Reduction.AEDS incorporates a novel affinity matching mechanism that identifies the most suitable edge cluster based on task characteristics, thereby significantly narrowing the decision search space. (2)Decision Process Optimization.AEDS adopts a hybrid strategy combining offline pre-training and online fine-tuning to address the cold start problem. Offline pre-training with historical task data ensures effective initial scheduling, while online fine-tuning periodically updates the DRL model to enhance long-term adaptability to dynamic system changes. (3)Decision Strategy Calibration.AEDS proposes a task migration solution to adapt to real-time workload variations dynamically. It utilizes triple queues to assess server overload and dynamically calibrates the scheduling strategy through task migration within interconnected clusters. Comprehensive experimental results validate the efficacy of AEDS. Compared with existing frameworks, AEDS reduces task latency by$28.23\%$and enhances task completion rate by$10.28\%$. Furthermore, by effectively narrowing the decision scope, AEDS accelerates the decision-making process by a remarkable$88.06\%$

Mixture of Experts (MoE) architectures have emerged as a promising paradigm for scaling model capacity through top-k routing mechanisms.Although reducing the number of activated experts inherently enables inference acceleration, this efficiency gain typically comes at the cost of significant performance degradation.To address this trade-off between efficiency and performance, we propose Hook-MoE, a plug-and-play single-layer compensation framework that effectively restores performance using only a small post-training calibration set.Our method strategically inserts a lightweight trainable Hook module immediately preceding selected transformer blocks.Comprehensive evaluations on four popular MoE models, with an average performance degradation of only 2.5% across various benchmarks, our method reduces the number of activated experts by more than 50% and achieves a 1.42× inference speed-up during the prefill stage.Through systematic analysis, we further reveal that the upper layers require fewer active experts, offering actionable insights for refining dynamic expert selection strategies and enhancing the overall efficiency of MoE models.We make our code available at https://github.com/KerwinKai/HookMoE.

Deep Neural Network (DNN) inference is a key enabler of edge intelligence, but its high computational demands and the imperative to protect the intellectual property of pretrained models present substantial challenges. Although recent research has started using Trusted Execution Environments (TEEs) for secure DNN inference, their limited memory and computational resources make it highly challenging to find an optimal balance between performance and security. To address this challenge, we propose Col-TEEs, a secure and efficient collaborative inference framework for heterogeneous TEEs. Col-TEEs strategically partitions the DNN inference process into device-side TEE and cloud-side TEE execution, aiming to maximize inference efficiency while ensuring model and data security. We first propose an optimal secure range determination method, which defines a secure interval by simulating model extraction and input reconstruction attacks, ensuring the confidentiality of pre-trained models and the privacy of user inputs. Furthermore, within this secure range, Col-TEEs employs an adaptive partitioning method that comprehensively evaluates the characteristics of heterogeneous TEE platforms. By combining a precise inference latency prediction model with heuristic algorithms, Col-TEEs dynamically selects the optimal partition point to balance security and inference performance. Additionally, Col-TEEs incorporates an integrity verification mechanism to secure intermediate data during network transmission. Extensive experiments demonstrate that Col-TEEs effectively balances performance and security, achieving an average$\mathbf{2. 9 8}$-fold increase in inference speed and a 63.54 % reduction in power consumption. Compared to collaborative inference without TEE protection, Col-TEEs introduces only a 4.65 % additional performance overhead.

Blockchain-based Federated Learning (BCFL) is widely recognized as a promising solution for collaboratively training machine learning models while maintaining system security. Since blockchain systems are transaction-driven, the efficiency of transaction processing is directly related to the performance and availability of the BCFL system. Previous research has primarily focused on optimizing storage mechanisms or integrating Trusted Execution Environment (TEE) to reduce transaction processing pressure. However, the performance of BCFL remains constrained by slow transaction processing. This critical bottleneck arises from scalar instruction operations in transaction execution engines and the inherent serial transaction processing mechanism. In this paper, we propose a novel hybrid-granularity parallelism architecture, HGP, to greatly accelerate transaction processing in BCFL systems. HGP achieves this through three major innovations: (1) a suite of extended vector instructions, which reduces the instruction number and execution latency by enabling vectorized data I/O and computation using very long instruction word (VLIW) techniques, (2) the scalable transaction grouping method that generates parallelizable transaction groups through transaction signature verification and read-write conflict detection, and (3) the multi-EVM (Ethereum Virtual Machine) parallel processing mechanism that processes a group of transactions using multiple execution engine threads, and maintains global consistency through group scheduling. Through these optimizations, HGP accelerates the transaction processing with both data-level and thread-level parallelism. We evaluate HGP by executing BCFL tasks over classic ResNet18, MobileNet, and SqueezeNet. The experimental results demonstrate that HGP achieves up to a$3.8 \times$improvement in CPU utilization and a$1.6 \times$improvement in memory utilization. Furthermore, HGP significantly speeds up the transaction processing performance of three critical tasks by up to$24.5 \times, 12.4 \times$, and$2.8 \times$, respectively.

Deep learning-based Synthetic Aperture Radar (SAR) ship image processing is essential in both civilian and military applications. However, training deep learning models requires a large dataset of high-resolution SAR ship images. Since SAR sensors are not readily available, obtaining an adequate number of such images remains a significant challenge. The SAR image generation technique is a useful way to create SAR ship images. However, many current methods depend only on location maps as input and do not incorporate guidance for the content of the SAR images, resulting in the production of low-quality images. To tackle these issues, we propose a novel content guided high resolution SAR ship image generation method. This approach incorporates SAR image-specific information to enhance the details of the generated images. We achieve this by separately fusing the input source image with both the source and target location maps, using them as guidance to steer the generation process. Additionally, to effectively transfer this guidance to the target SAR image, we introduce a Feature Transferring Module, which performs affine transformations based on scaling and shifting values learned by a Parameter Learning Module. Moreover, we design a Mask Transformer Module to learn the correlation weight and establish a fine-grained mapping between the source and target SAR images. To train and evaluate the proposed model, we have re-labeled the land and sea regions in the HRSID dataset for comparative analysis. Extensive experiments demonstrate that our model performs exceptionally well in the high-resolution SAR image generation task.

In the field of synthetic aperture radar (SAR) image analysis, the main challenges include the difficulty of eliminating the effects of ambient noise, the variability of objects, and the distinction between targets and nontargets. To address these issues, we propose a novel detection model, VFMDet, based on brain-inspired visual filtering mechanism. The model comprises two primary components: a brain-inspired filtering module and a SAR ship detection module. The former contains a bottom-up filtering module responsible for low-level feature extraction, an up-bottom filtering module responsible for high-level feature extraction, and a brain-inspired fusion module responsible for fusing the original image with the filtered feature map. In the SAR ship detection process, to accurately regress the orientation of the ship, we introduce a five-point coding scheme in polar coordinate system. Meanwhile, we introduce a Gaussian heatmap strategy (GHS) that utilizes limited covariance and a Gaussian heatmap loss to solve the problem caused by large-scale variation and dense arrangement of ship target. Finally, we design a multitask loss to help the model complete the end-to-end training. We conducted experiments on the rotating SAR ship detection dataset (RSSDD) and the rotating ship detection dataset (RSDD), and the mean average precision (mAP) improved by 0.27% and 0.89%, respectively, compared with the detection results of the best SAR image rotating object detection model.

The traditional two-dimensional (2D) barcode has been employed in anti-counterfeiting systems as a storage media for serial numbers. However, an attack can be initiated by simply copying the 2D barcode and attaching it to a counterfeit product. In this paper, we aim at proposing an authentication scheme with a mobile imaging device for a 2D barcode. This work presents a competitive solution among the 2D barcode authentication schemes that have been verified under mobile imaging conditions. The proposed copy-proof scheme is composed of two sets of features which are extracted by exploiting the characteristics of barcoding channel models. The proposed features identify the intrinsic differences between genuine and counterfeit barcode images in the frequency and spatial domains. An efficient two-stage barcode authentication framework is then proposed by combining the two sets of features in a cascading manner. To evaluate the practicality of the proposed authentication scheme, four databases with different devices (printers, scanners, mobile cameras), barcode sizes, and barcode designs are considered in the experiments. By comparing with the existing texture descriptors and some deep learning-based approaches, it is shown that the proposed scheme has a higher authentication accuracy under various conditions, such as cross-database, cross-size and cross-pattern experiments which study the generalities of a pre-trained model towards challenging conditions commonly found in real-world scenarios. Last but not least, the proposed scheme has been evaluated under some state-of-the-art attack scenarios where the attacker employs several realizations of genuine patterns or the deep learning-based technique to produce a counterfeit copy. The source code and data for producing the results in our experiments are available at https://bit.ly/2FOlJH7.