In recent years, Contrastive Language-Image Pretraining (CLIP) has been widely applied to Weakly Supervised Semantic Segmentation (WSSS) tasks due to its powerful cross-modal semantic understanding capabilities. This paper proposes a novel Semantic and Spatial Rectification (SSR) method to address the limitations of existing CLIP-based weakly supervised semantic segmentation approaches: over-activation in non-target foreground regions and background areas. Specifically, at the semantic level, the Cross-Modal Prototype Alignment (CMPA) establishes a contrastive learning mechanism to enforce feature space alignment across modalities, reducing inter-class overlap while enhancing semantic correlations, to rectify over-activation in non-target foreground regions effectively; at the spatial level, the Superpixel-Guided Correction (SGC) leverages superpixel-based spatial priors to precisely filter out interference from non-target regions during affinity propagation, significantly rectifying background over-activation. Extensive experiments on the PASCAL VOC and MS COCO datasets demonstrate that our method outperforms all single-stage approaches, as well as more complex multi-stage approaches, achieving mIoU scores of 79.5% and 50.6%, respectively.

Public Blockchain-based covert transmission (CT) can address the limitations of traditional CT methods. Monero is a blockchain-based cryptocurrency with strong privacy protection techniques. However, existing Monero-based CT methods are limited to unicast scenarios. If applied directly to group CT scenarios, they would lead to a significant increase in transaction volume as the number of receivers increases. Meanwhile, existing Bitcoin/Ethereum-based group CT methods at least face three challenges, including susceptibility to key and identity inference attacks, information leakage during off-chain negotiations, and exposure of communication channels.This paper proposes a Monero-Based Group CT approach (MBGCT), which enables on-chain group key (used for receivers to filter covert transactions and extract messages) issuance, fine-grained access control of messages, and covert transaction identification and decryption isolation. MBGCT can ensure confidentiality of group keys, unforgeability of messages, integrity of each transmitted message, obscurity of covert channels, isolation of key generation from key management, and enhanced anonymity. As a result, MBGCT can not only prevent information leakage and channel exposure, but also resist the attacks of entity impersonation, data tampering, key and identity inference. We implemented MBGCT in Monero client v0.18.1.0, and validated its capability of high embedding rates, low transaction fees, and high execution efficiency on the Monero public chain Stagenet.

The rapid growth of the low-altitude economy has driven the widespread adoption of unmanned aerial vehicles (UAVs). This growing deployment presents new challenges for UAV trajectory planning in complex urban environments. However, existing studies often overlook key factors, such as urban airspace constraints and economic efficiency, which are essential in low-altitude economy contexts. Deep reinforcement learning (DRL) is regarded as a promising solution to these issues, while its practical adoption remains limited by low learning efficiency. To overcome this limitation, we propose a novel UAV trajectory planning algorithm that integrates DRL with the large language model (LLM) reasoning to enable safe, compliant, and economically viable trajectory planning. Specifically, we model the trajectory planning task as a partially observable Markov decision process, explicitly incorporating obstacle avoidance, regulation awareness, and energy constraints. We design a hybrid optimization algorithm based on the soft actor-critic algorithm and LLM reasoning to enable adaptive decision-making in uncertain and dynamic environments. Experimental results demonstrate that our algorithm achieves the best overall performance, with the highest data collection rate (99.50%), almost zero collision avoidance rate and regulation violation rate, a successful landing rate of nearly 100%, and the lowest energy consumption rate (76.95%). These results validate the effectiveness of our algorithm in addressing UAV trajectory planning key challenges under constraints of the low-altitude economy networking.

Availability and/or performance of PBFT (Practical Byzantine Fault Tolerance) consensus service has been widely studied. However, the existing studies overlook the situation of software aging of honest nodes, which can degrade system performance over time. Rejuvenation techniques can mitigate the negative impact of aging. This paper aims to make a quantitative joint analysis of availability and performance (a.k.a performability) of PBFT consensus service in the scenario where honest nodes are susceptible to software aging and rejuvenation techniques are adopted for recovery. We propose a Semi-Markov process (SMP) based approach for model-based evaluation. Unlike traditional models that rely on exponential distributions, our approach allows the time intervals of all events to follow general distributions, thereby enable a more nuanced analysis of PBFT dynamics. We detail the modeling process and the derivation of metric formulas. We also carry out numerical analysis for the evaluation to assess the performability of PBFT consensus service.

Attack-path planning plays a key role in proactive cybersecurity because of its ability in helping defenders anticipate adversaries and uncover critical vulnerabilities. This paper proposes GAPPO, a novel deep reinforcement learning-based attack path planning scheme that integrates Graph Attention Networks (GAT) and expert knowledge into Proximal Policy Optimization (PPO). There are three mechanisms in GAPPO. The first is using GAT to produce graph-structure-aware embeddings that emphasize critical connections, enabling expressive state representations for decision making. The second is a ruled-based action masking mechanism, which incorporates expert knowledge to prune the action space based on node dependencies and then to prevent illegal actions from negatively impacting training. The third is combining the results of the first two mechanisms into PPO for attack path planning. Our extensive experimental results demonstrate that GAPPO outperforms existing methods in terms of faster convergence and higher-quality attack paths across diverse scenarios.

Abstract Automated segmentation of mitochondria is crucial for statistical analysis in biological research. Existing segmentation techniques often face challenges with fluorescence images. Handcrafted methods have poor segmentation results while deep learning‐based methods lack the labeled mitochondrial data. However, although the number of labeled mitochondrial images is limited, the unlabeled fluorescent data is easy to obtain. The authors aim to leverage a large amount of unlabeled data to learn mitochondrial morphological features. The approach begins with self‐supervised learning from a vast set of unlabeled images through masked image modeling. This technique involves presenting images with randomly masked patches, prompting the model to predict the content of these masked areas. By doing so, the model learns the distinctive features of mitochondria. In the subsequent phase, the trained encoder is transferred to the segmentation task, replacing the original reconstruction decoder with the Segformer segmentation decoder. The model is then fine‐tuned using a small labeled dataset. By reconstructing mitochondria in the masked regions, the model learns features more effectively on unlabeled samples, and improves segmentation performance even with limited labeled data. Empirical results validate the effectiveness of the approach, showing an 11.8% improvement in Intersection over Union metrics compared to existing fluorescence mitochondrial segmentation techniques.

Existing research has demonstrated that autonomous driving policies based on deep reinforcement learning (DRL) are vulnerable to adversarial attacks, which poses challenges for the practical deployment of these policies. Designing effective adversarial attacks is a crucial prerequisite for building robust driving policies. In view of this, we propose a novel adversarial attack method, which can attack the DRL-based autonomous driving agents in a stealthy and efficient manner. This method models the attack as a mixed-integer optimization problem that aims to maximize the safety violations (e.g., collisions) of the agents while minimizing the number of attack steps. Then, a DRL-based adversary is devised in this method to solve the problem to automatically learn the optimal attack policy without domain knowledge. To further enhance the adversarys learning capability, this method incorporates attack-related information into its observations to provide more decisionmaking context and employ a trajectory clipping technique to enhance sample quality. Extensive evaluation results reveal that our method achieves a remarkable 105% enhancement in attack efficiency compared to existing methods.

Data provision, referring to data upload and data access, is one key phase in vehicular digital forensics. The unique features of driverless taxi (DT) bring new issues to this phase: I1) efficient verification of data integrity when diverse data providers (DPs) upload data; I2) DP privacy preservation during data upload; and I3) privacy preservation of both data and investigator (IN) under complex data ownership when accessing data. Considering that the existing works on digital forensics cannot address all these issues, we first propose a novel lightweight and privacy-preserving data provision (LPDP) approach consisting of three mechanisms: 1) privacy-friendly batch verification mechanism (PBVm); 2) data access control mechanism (DACm); and 3) decentralized IN warrant issuance mechanism (DIWIm). PBVm ensures scalable verification of data integrity to address I1. PBVm also ensures the DP privacy preservation in terms of the location privacy and unlinkability of data upload requests to address I2. Besides, DACm and DIWIm are combined to ensure data privacy preservation and the identity privacy of IN in terms of the anonymity and unlinkability of data access requests without sacrificing the traceability to address I3. Security analysis and performance evaluations validate LPDP’s capabilities in addressing the three issues.

Driverless taxis (DTs) are gaining attention for their potential to improve urban transportation efficiency. However, unforeseen incidents caused by unsupervised users and the personalized needs of passengers in DTs highlight the need for authenticating user identities and attributes. Additionally, protecting user privacy while enabling rapid traceability of malicious users remains a challenge for the widespread adoption of DTs. This paper proposes a novel Attribute-based Anonymity Enhanced (A2E) authentication scheme for users to access DT services. The security capabilities of A2E include: 1) A2E is attribute-based authentication, which is achieved by designing a user attribute credential. Meanwhile, this attribute credential also satisfies unlinkability. And 2) A2E has enhanced anonymity, which is achieved by designing a decentralized credential issuance mechanism, safeguarding user attributes from association with anonymous identities. Moreover, this mechanism provides traceability and non-frameability to users. From the performance aspect, A2E causes low overhead when tracing malicious users and updating credentials. Besides, both scalability and lightweight are satisfied, which contributes to A2E’s practicability. We conduct security and performance analysis to validate these capabilities.

Traditional covert transmission (CT) approaches have been hindering CT application while blockchain technology offers new avenue. Current blockchain-based CT approaches require off-chain negotiation of critical information and often overlook the dynamic updating of session keys, which increases the risk of message and key leakage. Additionally, in some approaches the covert transactions exhibit obvious characteristics that can be easily detected by third-parties. Moreover, most approaches do not address the issue of decreased reliability of message transmission in blockchain attack scenarios. Bitcoin-and Ethereum-based approaches also have the issue of transaction linkability, which can be tackled by Monero-based approaches because of the privacy protection mechanisms in Monero. However, Monero-based CT has the problem of sender repudiation. In this paper, we propose a novel$M$onero-$B$ased CT approach (MBCT), which enables on-chain session key dynamically updating without off-chain negotiation. MBCT can assure confidentiality of on-chain session key, non-repudiation of transmission parties, reliability of message transmission under blockchain attack, unlinkability and obscurity of covert transactions. They are achieved by the three components in MBCT, namely, a sender authentication method, a dynamically on-chain session key updating method and a state feedback method. We implement MBCT in Monero-0.18.1.0 and the experiment results demonstrate its high embedding capacity of MBCT.

Unmanned aerial vehicles (UAVs) are being broadly employed to assist in efficient data collection for Internet of Things (IoT) networks. Studies have been conducted to ensure the effectiveness and safety of UAVs in the data collection process. However, they only considered part of the challenges of energy consumption, collision avoidance, and mobility of IoT devices. In this article, we study a UAV path planning optimization problem for UAV-assisted data collection to maximize the amount of collected data. Different from these existing works, this optimization problem not only considers all these challenges, but also considers the kinematic and communication constraints. Moreover, in this problem, the duration required for the UAV to complete the mission is unknown, makes it more challenging to solve this problem through traditional optimization methods. We thus formulate the problem as a partially observable Markov decision process (POMDP) with a continuous action space and propose a proximal policy optimization-based algorithm to address it. Experiment results demonstrate that our algorithm has significant advantages over other baseline algorithms in terms of success rate, data collection rate, and collision rate.

Recently, big data has seen explosive growth in the Internet of Things (IoT). Multi-layer FL (MFL) based on cloud-edge-end architecture can promote model training efficiency and model accuracy while preserving IoT data privacy. This paper considers an improved MFL, where edge layer devices own private data and can join the training process. iMFL can improve edge resource utilization and also alleviate the strict requirement of end devices, but suffers from the issues of Data Reconstruction Attack (DRA) and unacceptable communication overhead. This paper aims to address these issues with iMFL. We propose a Privacy Amplification scheme on iMFL (PA-iMFL). Differing from standard MFL, we design privacy operations in end and edge devices after local training, including three sequential components, local differential privacy with Laplace mechanism, privacy amplification subsample, and gradient sign reset. Benefitting from privacy operations, PA-iMFL reduces communication overhead and achieves privacy-preserving. Extensive results demonstrate that against State-Of-The-Art (SOTA) DRAs, PA-iMFL can effectively mitigate private data leakage and reach the same level of protection capability as the SOTA defense model. Moreover, due to adopting privacy operations in edge devices, PA-iMFL promotes up to 2.8 × communication efficiency than the SOTA compression method without compromising model accuracy.

This article investigates a hierarchical aerial computing system, where both high-altitude platforms (HAPs) and unmanned aerial vehicles (UAVs) provision computation services for ground devices (GDs). Different from the existing works which ignored UAV task offloading to HAPs and suffered long transmission delay between HAPs and GDs, in our system, UAVs are responsible for collecting the tasks generated by GDs. Considering limited resources and constrained coverage, UAVs need to cooperatively allocate their resources (including spectrum, caching, and computing) to GDs. After collecting GD tasks, UAVs are allowed to offload part of these tasks to the HAP, in order to minimize task processing delay and then better satisfy GD delay requirement. Our objective is to maximize the amount of computed tasks while satisfying tasks’ heterogeneous Quality-of-Service (QoS) requirements through the joint optimization of UAV resource allocation and task offloading. To this end, a joint optimization problem is first formulated as a partially observable Markov decision process (POMDP) under the constraints of available resources, UAV energy, and collision avoidance. Then, we design a multiagent proximal policy optimization (MAPPO)-based algorithm to solve the optimization problem. By introducing the centralized training with decentralized execution framework, UAVs acting as agents can cooperatively make decisions on GDs association, resource allocation, and task offloading according to their local observations. In addition, state normalization and action mask are also adopted to improve training efficiency. Experimental results verify the efficiency of the proposed algorithm and the system performance is also analyzed by the numerical results.

Automatically segmenting the anatomical structure of the heart from the cardiac magnetic resonance (CMR) images offers a great potential to augment the traditional healthcare strategy for the quantitative analysis of cardiac contractile function. Most of the existing CNN-based methods for cardiac segmentation tend to ignore the misalignment issues during the feature aggregation process and not fully use multi-scale context and contour information, which may lead to the unexpected misclassification caused by the falsely aligned contextual features and the discontinuity in the edge of segmentation maps. To resolve these issues, we proposed a context correlation aware network (CCA-Net). In CCA-Net, a volume correlation flow module was designed to align contour features and semantic features from adjacent levels, which offered the guidance to wrap low-resolution semantic features into high-resolution features. Besides, a residual gated squeeze module was utilized to explicitly model the boundaries and enhance the representations. Extensive experiments on the multi-sequence cardiac magnetic resonance segmentation challenge (MS-CMRSeg 2019) dataset and MICCAI challenge 2017 automatic cardiac diagnosis challenge (ACDC) dataset demonstrated that CCA-Net was superior to other state-of-the-art methods.

Abstract For image contrast enhancement operation, it is a keypoint to obtain more natural enhanced results and keep more details without distortion. In this paper, a novel image Hessian‐matrix weighted histogram for image contrast enhancement is proposed, which can improve the contrast of smooth regions and simultaneously restrain the contrast of texture regions. In the proposed method, the multi‐scale fractional‐order Hessian‐matrix is firstly utilized to detect and quantify the texture information of the input image, which explores the regions that should be contrasted or should be restrained. Then, the strong texture regions are suppressed by a designed suppress function. Finally, the information on unsuppressed regions and suppressed texture regions will be count by a histogram, which is termed as Hessian‐matrix weighted Histogram (HessHist) in this paper. According to HessHist, the corresponding cumulative distribution function will realize the contrast enhancement operation on the input image. For real‐time application, the integral images are introduced for fast computation of the HessHist. Experimental results show that the proposed HessHist‐based image enhancement algorithm preserves more details of input image without distortion, and is competitive with state‐of‐the‐art image enhancement algorithms in both subjective visual perception and objective evaluation metrics.