Crowdsensing has gained widespread attention due to its efficient and low cost data collection mode that leverages a large number of intelligent mobile devices. Privacy and data quality are two key concerns in crowdsensing. Recently, extensive efforts have been devoted to privacy-preserving truth discovery (PPTD), which aims to protect sensitive data while improving data quality. However, existing PPTD schemes suffer from either low reliability—especially under collusion attacks and server dropout—or low communication efficiency. As a result, they fail to meet the practical requirements of real-time processing with high reliability. To address the problems, we propose FPTD, a super fast PPTD scheme for crowdsensing that provides$T$-out-of-$N$threshold reliability, with a focus on boosting online efficiency. Our scheme employs edge nodes as servers in a multi-server architecture, resisting up to ($T-1$) colluding servers and ($N-T$) server dropouts. We construct novel protocols for PPTD, including secure division and negative of approximate logarithms. We further significantly improve communication efficiency by designing protocolsmultiply-then-divide,dot-product-then-divide, andfilter-then-dot-product-then-divide, all of which require only a single element per party in online communication. Our tradeoff is a need for a circuit-dependent offline phase, which is independent of the parties' inputs. Compared to the state-of-the-art scheme, we are 13$\sim 217\times$faster (LAN) and 17$\sim 190 \times$faster (WAN) in online execution time.

The right to be forgotten, mandated by modern privacy regulations, poses unique challenges to federated learning in medical imaging, where models must erase patient-specific information while preserving diagnostic utility. Existing federated unlearning (FU) methods struggle with this trade-off due to the high privacy sensitivity and spatial complexity of medical data. To address these challenges, we propose LAFUL, a lesion-aware federated unlearning framework designed for privacy-preserving medical image analysis. LAFUL exploits the spatial sparsity and semantic focus of pathological lesions to identify and selectively mask lesion-sensitive gradient channels, effectively removing private information while retaining anatomy-relevant representations. To mitigate distributional shifts caused by targeted gradient removal, a feature-level knowledge distillation module aligns intermediate representations using an unlabeled proxy dataset. Experiments on two public benchmarks—intracranial hemorrhage detection and skin lesion classification—show that LAFUL achieves near-retrained accuracy with over$9 \times$efficiency improvement, providing an interpretable and practical solution for scalable FU in healthcare.

The convergence of healthcare and financial technology has driven the adoption of federated learning (FL) for collaborative analysis of sensitive data across distributed systems. However, existing approaches face critical challenges, particularly gradient inversion attacks that can reconstruct raw patient data from shared parameters, compromising clinical confidentiality. While FL integrated with conditional generative adversarial networks (GANs) shows promise for medical applications, sharing generator parameters still poses substantial privacy risks. As AI technologies proliferate and the demand for telemedicine expands, the need for secure medical fintech solutions increases, requiring robust mechanisms to protect shared parameters and medical data. To address these limitations, we propose CryptoGAN, a novel approach that embeds a GAN into the client’s local network, aligns the generator’s output distribution with the feature distribution of local data, and aggregates the client’s information by uploading homomorphically encrypted generator parameters. This approach ensures that not only can leakage of local data features be prevented but also the sensitive medical information embedded in the generator parameters is protected, thus improving the privacy of medical applications. Extensive experiments on medical datasets demonstrated that CryptoGAN effectively protects patient privacy while maintaining high diagnostic accuracy and outperforms traditional FL methods in the healthcare domain.

Truth discovery is an effective technique for resolving data conflicts in crowdsensing. Fog-based mobile crowdsensing utilizes low-latency and high-efficiency communications capabilities of fog computing to achieve large-scale data sensing at a low cost. Privacy-preserving truth discovery (PPTD) has garnered significant attention in recent years due to the inclusion of users’ sensitive information in sensory data. However, existing PPTDs have not adequately addressed fog servers’ reliability and mobile devices’ efficiency simultaneously. Challenges are that fog servers are susceptible to breakdowns and collusion that causes privacy breaches, while mobile devices have limited resources. We thus propose a reliable and efficient PPTD for fog-based crowdsensing. We employ a threshold secret sharing scheme to establish secure multi-party computation primitives. These primitives are then used to construct an arithmetic circuit–an essential component of the PPTD. This approach preserves privacy of sensory data, as well as intermediate and final results, while accounting for server collusion, dropout, and mobile devices’ efficiency. It has$T$-out-of-$N$threshold reliability that resists ($T-1$) servers’ collusion and ($N-T$) servers’ dropout. Experimental results demonstrate that our scheme reduces worker processing time by at least one order of magnitude and network communication overhead by approximately two orders of magnitude compared to existing PPTD methods.

Human intelligence tasks (HITs) are widely utilized for crowdsourcing human knowledge, such as labeling images for machine learning. Centralized crowdsourcing platforms face challenges of a single point of failure and a lack of service transparency. Existing blockchain-based crowdsourcing approaches overlook the low scalability problem of permissionless blockchains or inconveniently rely on existing ground-truth data as the root of trust to evaluate quality of workers' answers. We propose a blockchain-based crowdsourcing scheme for ensuring dual fairness (i.e., preventing false-reporting and free-riding) and improving on-chain efficiency concerning on-chain storage and smart contract computation. The proposed scheme does not rely on trusted authorities but rather depends on a public blockchain to guarantee the dual fairness. An efficient and publicly verifiable truth discovery scheme is designed based on majority voting and cryptographic accumulators. This truth discovery scheme aims at inferring ground truth from workers' answers. The ground truth is further utilized to estimate the quality of workers' answers. Additionally, a novel blockchain-based protocol is designed to further reduce on-chain costs while ensuring truthfulness. The scheme has O(n) complexity for both on-chain storage and smart contract computation, regardless of the number of questions, where n denotes the number of workers. Formal security analysis is provided, and extensive experiments are conducted to evaluate effectiveness and performance.

Machine learning (ML) has led to disruptive innovations in many fields, such as medical diagnoses. A key enabler for ML is large training data, but existing data, such as medical data, are not fully exploited by ML because of data silos and privacy concerns. Federated learning (FL) is a promising distributed learning paradigm to address this problem. On the other hand, existing FL approaches are vulnerable to poisoning attacks or privacy leakage from a malicious aggregator or client. This article proposes an auditable FL scheme with Byzantine robustness against the aggregator and client: The aggregator is malicious but available, and the client could perform poisoning attacks. First, the Pedersen commitment scheme (PCS) for homomorphic encryption was applied to preserve privacy and for commitments to the FL process to achieve auditability. The auditability enables clients to verify the correctness and consistency of the entire FL process and to identify parties that misbehave. Second, an efficient technique of divide and conquer was designed based on PCS to allow parties to cooperate and securely aggregate gradients to defend against poisoning attacks. This technique enables clients to share no common secret key and cooperate to decrypt ciphertext, guaranteeing a client’s privacy even if some other clients are corrupted by adversaries. This technique was optimized to tolerate the dropout of clients. This article reports a formal analysis concerning privacy, efficiency, and auditability against malicious participants. Extensive experiments on various benchmark datasets show that the scheme is robust with high model accuracy against poisoning attacks.

Three-dimensional images are frequently used in medical imaging research for classification, segmentation, and detection. However, the limited availability of 3D images hinders research progress due to network training difficulties. Generative methods have been proposed to create medical images using AI techniques. Nevertheless, 2D approaches have difficulty dealing with 3D anatomical structures, which can result in discontinuities between slices. To mitigate these discontinuities, several 3D generative networks have been proposed. However, the scarcity of available 3D images makes training these networks with limited samples inadequate for producing high-fidelity 3D images. We propose a data-guided generative adversarial network to provide high fidelity in 3D image generation. The generator creates fake images with noise using reference code obtained by extracting features from real images. The generator also creates decoded images using reference code without noise. These decoded images are compared to the real images to evaluate fidelity in the reference code. This generation process can create high-fidelity 3D images from only a small amount of real training data. Additionally, our method employs three types of discriminator: volume (evaluates all the slices), slab (evaluates a set of consecutive slices), and slice (evaluates randomly selected slices). The proposed discriminator enhances fidelity by differentiating between real and fake images based on detailed characteristics. Results from our method are compared with existing methods by using quantitative analysis such as Fréchet inception distance and maximum mean discrepancy. The results demonstrate that our method produces more realistic 3D images than existing methods.

Accurately segmenting polyps from colonoscopy images is essential for diagnosing colorectal cancer. Despite the tremendous success of the deep convolutional neural networks in automatic polyp segmentation, it suffers from domain shift issues, where the trained model yields performance deterioration on unseen test datasets. This paper proposes an illumination enhancement-based domain generalization approach to improve the generalization capability of the model on unseen test datasets and alleviate this issue. In particular, an image decomposition module (IDM) was developed to separate colonoscopy images into reflectance, local, and global illumination components. An illumination transform module (ITM) was proposed to augment images with different global illuminations by synthesizing target-like global illumination maps. A novel illumination variance insensitiveness (IViSen) is also introduced to evaluate the robustness of the model against illumination disturbance. IViSen is easy to compute and correlates well with model generalizability. The segmentation performance of the proposed model on four colonoscopy datasets was examined: CVC-ClinicDB, CVC-ColonDB, ETIS-Larib, and Kvasir-SEG. The method outperformed the competitive methods when tested on unseen domains. In particular, the proposed approach yielded 60.82% and 53.19% in terms of mean Dice and IoU, respectively, with 2.06% and 2.31% improvements.

This paper proposes a particle-based nonlinear elastic object simulation technique for virtual surgery. Particle-based techniques are used to model and simulate nonlinear elastic objects, such as the skin and internal organs. This enables the simulation to consider various factors, such as location, direction, and depth, when making incisions in the organs. However, the issue with this method is that it can only simulate precisely cut tissue during incision. Objects with elasticity, such as tissue, require the generation of complex debris during incision. This paper proposes a particle-based elastic object simulation technique to model the debris from torn tissue when making an incision in the organs. It can predict where the tissue will tear based on the maximum shear stress (MSS) theory and Tresca’s yield criterion when the force applied to the tissue exceeds the maximum stress. Newly generated particles at the predicted location are remeshed with nearby particles. We verified the superiority of our proposed method over traditional particle-based methods by accurately representing more complex debris and comparing the results of incisions in the same area of the body. This allows various incision types, such as stab wounds and lacerations, to be simulated.

Abstract We consider medical image transformation problems where a grayscale image is transformed into a color image. The colorized medical image should have the same features as the input image because extra synthesized features can increase the possibility of diagnostic errors. In this paper, to secure colorized medical images and improve the quality of synthesized images, as well as to leverage unpaired training image data, a colorization network is proposed based on the cycle generative adversarial network (CycleGAN) model, combining a perceptual loss function and a total variation (TV) loss function. Visual comparisons and experimental indicators from the NRMSE, PSNR, and SSIM metrics are used to evaluate the performance of the proposed method. The experimental results show that GAN-based style conversion can be applied to colorization of medical images. As well, the introduction of perceptual loss and TV loss can improve the quality of images produced as a result of colorization better than the result generated by only using the CycleGAN model.

Crowdsourcing for Human Intelligence Tasks (HIT) has been widely used to crowdsource human knowledge, such as image annotation for machine learning. We use a public blockchain to play the role of traditional centralized HIT systems, such that the blockchain deals with cryptocurrency payments and acts as a trustworthy judge to resolve disputes between a worker and a requester in a decentralized setting, preventing false-reporting and free-riding. Our approach neither uses expensive cryptographic tools, such as zero-knowledge proofs, nor sends the worker's answers to the blockchain. Compared with prior works, our approach significantly reduces on-chain cost: it only requires O(1) on-chain storage and O(log N ) smart contract computation, where N is the question number of a HIT. Additionally, our approach uses known answers or gold standards to determine the worker's answer quality. To motivate the requester to use honest known answers, the requester cannot learn the worker's answers if the answer quality does not meet the requirement. We further provide formal security definitions for our decentralized HIT and prove security of our construction.

Abstract We present a novel approximation of a global illumination technique called contour‐based polygonal ambient occlusion, an approach that darkens by only using a depth texture as screen‐space ambient occlusion without additional information such as a normal buffer. We introduce a discrete level structure to calculate the amount of occlusion by using the contour level, an integer value derived from the depth difference of neighboring texels. We use the uniform sampling to define the positions of the neighboring texels in the depth texture. Our method does not depend on geometric complexity because our method works in screen space and works well for both static and dynamic scenes without any precomputation. Copyright © 2013 John Wiley & Sons, Ltd.

Abstract Ultrasound imaging is widely used in medical areas. By transmitting ultrasound signals into the human body, their echoed signals can be rendered to represent the shape of internal organs. Although its image quality is inferior to that of CT or MR, ultrasound is widely used for its speed and reasonable cost. Volume rendering techniques provide methods for rendering the 3D volume dataset intuitively. We present a visualization framework for ultrasound datasets that uses programmable graphics hardware. For this, we convert ultrasound coordinates into Cartesian form. In ultrasound datasets, however, since physical storage and representation space is different, we apply different sampling intervals adaptively for each ray. In addition, we exploit multiple filtered datasets in order to reduce noise. By our method, we can determine the adequate filter size without considering the filter size. As a result, our approach enables interactive volume rendering for ultrasound datasets, using a consumer‐level PC. Copyright © 2009 John Wiley & Sons, Ltd.

Shear–warp volume rendering has the advantages of a moderate image quality and a fast rendering speed. However, in the case of dynamic changes in the opacity transfer function, the efficiency of memory access drops, as the method cannot exploit pre-classified volumes. In this paper, we propose an efficient algorithm that exploits the spatial locality of memory references for interactive classifications. The algorithm inserts a rotation matrix when factorizing the viewing transformation, so that it may perform a scanline-based traversal in both object space and image space. In addition, we present solutions to some problems of the proposed method, namely inaccurate front-to-back composition, the occurrence of holes, and increased computation. Our method is noticeably faster than traditional shear-warp rendering methods because of an improved utilization of cache memory. Copyright © 2005 John Wiley & Sons, Ltd.

Abstract Interactive display of complex scenes is a challenging problem in computer graphics. Such current approaches as z‐buffer, level of detail and visibility culling have not fully used the temporal coherence between consecutive frames. When the viewing condition is fixed, the color and depth values of static polygons can be obtained from the result of the previous frame and only the remaining dynamic polygons require rendering. We present a method that enhances the speed of the conventional z‐buffer algorithm by exploiting the above temporal coherence. This algorithm is simple to combine with existing graphics hardware that supports the conventional z‐buffer algorithm. It can manipulate any scene suitable for the z‐buffer algorithm without preprocessing or human intervention. The rendering time is proportional to the number of dynamic polygons in each frame. Experimental results show that our method is faster than the conventional z‐buffer algorithm and the performance enhancement becomes higher as the fraction of static polygons increases. Copyright © 2001 John Wiley & Sons, Ltd.

Shading an object is to simulate the behaviour of light incident on its surfaces. It is necessary to calculate normal vectors on the surfaces of the object for shading it. Since objects do not contain surface inclination in voxel-based representation, a normal vector for each voxel must be estimated from the relative position of its neighbouring voxels that have the same data value. The previously devised methods that use fixed-size gradient operators can estimate normal vectors accurately only in a limited area and may cause some errors and artefacts. In this paper we propose an efficient normal estimation method using an extended central difference operator whose size can vary according to the arrangement of surface-comprising voxels. This method calculates normals more accurately than the previous methods and its computation time is shorter than that of methods that guarantee the same image quality. In order to show the improvement, we compare the quality of resulting images and processing time by implementing the newly proposed method and the previous methods and then applying them to some volume data. Copyright © 1999 John Wiley & Sons, Ltd.

To visualize the volume data acquired from computation or sampling, it is necessary to estimate normals at the points corresponding to object surfaces. Volume data does not holds the geometric information for the surface comprising points, so it is necessary to calculate normals using local information at each point. The existing normal estimation methods have some problems of estimating incorrect normals at discontinuous, aliased or noisy points. Yagel et al. (1992) solved some of these problems using their context-sensitive method. However, this method requires too much processing time and it loses some information on detailed parts of the object surfaces. This paper proposes the surface-characteristic-sensitive normal estimation method which applies different operators according to characteristics of each surface for the normal calculation. This method has the same advantages of the context-sensitive method, and also some other advantages such as less processing time and the reduction of the information loss on detailed parts.