Search Results (170)

Autonomous navigation in cluttered and dynamic industrial environments remains a major challenge for mobile robots. Traditional occupancy-grid and geometric planning approaches often struggle in such unstructured settings due to partial observability, sensor noise, and the frequent presence of moving agents (machinery, vehicles, humans). These limitations seriously undermine long-term reliability and safety compliance—both essential for Industry 4.0 applications. This paper introduces S3PM, a lightweight entropy-regularized framework for simultaneous mapping and path planning that operates directly on dense 3D point clouds. Its key innovation is a dynamics-aware entropy field that fuses per-voxel occupancy probabilities with motion cues derived from residual optical flow. Each voxel is assigned a risk-weighted entropy score that accounts for both geometric uncertainty and predicted object dynamics. This representation enables (i) robust differentiation between reliable free space and ambiguous/hazardous regions, (ii) proactive collision avoidance, and (iii) real-time trajectory replanning. The resulting multi-objective cost function effectively balances path length, smoothness, safety margins, and expected information gain, while maintaining high computational efficiency through voxel hashing and incremental distance transforms. Extensive experiments in both real-world and simulated settings, conducted on a Raspberry Pi 5 (with and without the Hailo-8 NPU), show that S3PM achieves 18–27% higher IoU in static/dynamic segmentation, 0.94–0.97 AUC in motion detection, and 30–45% fewer collisions compared to OctoMap + RRT* and standard probabilistic baselines. The full pipeline runs at 12–15 Hz on the bare Pi 5 and 25–30 Hz with NPU acceleration, making S3PM highly suitable for deployment on resource-constrained embedded platforms. Full article

With the rapid advancements in technology, there has been a noticeable increase in phishing attacks that exploit users by impersonating trusted entities. The primary attack vectors include fraudulent websites and carefully crafted emails. Early detection of such threats enables the more effective blocking of malicious sites and timely user warnings. One of the key elements in phishing detection is identifying the entity being impersonated. In this article, we conduct a comparative analysis of methods for detecting phishing websites that rely on website screenshots and recognizing their impersonation targets. The two main research objectives include binary phishing detection to identify malicious intent and multiclass classification of impersonated targets to enable specific incident response and brand protection. Three approaches are compared: two state-of-the-art methods, Phishpedia and VisualPhishNet, and a third, proposed in this work, which uses perceptual hash similarity as a baseline. To ensure consistent evaluation conditions, a dedicated framework was developed for the study and shared with the community via GitHub. The obtained results indicate that Phishpedia and the Baseline method were the most effective in terms of detection performance, outperforming VisualPhishNet. Specifically, the proposed Baseline method achieved an F1 score of 0.95 on the Phishpedia dataset for binary classification, while Phishpedia maintained a high Identification Rate (>0.9) across all tested datasets. In contrast, VisualPhishNet struggled with dataset variability, achieving an F1 score of only 0.17 on the same benchmark. Moreover, as our proposed Baseline method demonstrated superior stability and binary classification performance, it should be considered as a robust candidate for preliminary filtering in hybrid systems. Full article

Streaming media data have become pervasive in modern commercial systems. To address large-scale data processing in intelligent transportation systems (ITSs), recent research has focused on deep neural network–based (DNN-based) approaches to improve the performance of cross-modal hashing retrieval (CMHR) systems. However, due to their high dimensionality and network depth, DNN-based CMHR systems inherently suffer from vulnerabilities to malicious adversarial examples (AEs). This paper investigates the robustness of CMHR-based ITS systems against AEs. Prior work typically formulates AE generation as an optimization-driven, iterative process, whose high computational cost and slow generation speed limit research efficiency. To overcome these limitations, we propose a parallel cross-modal relevance-guided generative network (ReGeNet) that captures the semantic characteristics of the target deep hashing model. During training, we design a relevance-guided adversarial generative framework to efficiently learn AE generation. During inference, the well-trained parallel adversarial generator produces adversarial cross-modal data with effectiveness comparable to that of iterative methods. Experimental results demonstrate that ReGeNet can generate AEs significantly faster while achieving competitive attack performance relative to iterative-based approaches. Full article

This paper introduces Graph-Propagated Multi-Scale Hashing with Contrastive Learning (GPMCL), a novel unsupervised cross-modal hashing framework designed to address the semantic deficiency in large-scale unlabeled multimodal data. GPMCL first constructs an initial similarity matrix via cross-modal graph propagation, effectively capturing potential inter-modal relationships. A multi-scale enhancement strategy is then employed to integrate both local and global similarities, resulting in a more informative and robust similarity representation. To adaptively distinguish sample relationships, a Gaussian Mixture Model (GMM) is utilized to determine dynamic thresholds. Additionally, contrastive learning is incorporated in the feature space to enhance intra-class compactness and inter-class separability. Extensive experiments conducted on three public benchmark datasets demonstrate that GPMCL consistently outperforms existing state-of-the-art unsupervised cross-modal hashing methods in terms of retrieval performance. These results validate the effectiveness and generalization capability of the proposed method, highlighting its potential for practical cross-modal retrieval applications. Full article

The rapid convergence of artificial intelligence (AI), cloud computing, and 5G communication has positioned extended reality (XR) as a core technology bridging the physical and virtual worlds. Encompassing virtual reality (VR), augmented reality (AR), and mixed reality (MR), XR has demonstrated transformative potential across sectors such as healthcare, industry, education, and defense. However, the compact architecture and limited computational capabilities of XR devices render conventional cryptographic authentication schemes inefficient, while the real-time transmission of biometric and positional data introduces significant privacy and security vulnerabilities. To overcome these challenges, this study introduces PXRA (PUF-based XR authentication), a lightweight and secure authentication and key distribution protocol optimized for cloud-assisted XR environments. PXRA utilizes a physically unclonable function (PUF) for device-level hardware authentication and offloads elliptic curve cryptography (ECC) operations to the cloud to enhance computational efficiency. Authenticated encryption with associated data (AEAD) ensures message confidentiality and integrity, while formal verification through ProVerif confirms the protocol’s robustness under the Dolev–Yao adversary model. Experimental results demonstrate that PXRA reduces device-side computational overhead by restricting XR terminals to lightweight PUF and hash functions, achieving an average authentication latency below 15 ms sufficient for real-time XR performance. Formal analysis verifies PXRA’s resistance to replay, impersonation, and key compromise attacks, while preserving user anonymity and session unlinkability. These findings establish the feasibility of integrating hardware-based PUF authentication with cloud-assisted cryptographic computation to enable secure, scalable, and real-time XR systems. The proposed framework lays a foundation for future XR applications in telemedicine, remote collaboration, and immersive education, where both performance and privacy preservation are paramount. Our contribution lies in a hybrid PUF–cloud ECC architecture, context-bound AEAD for session-splicing resistance, and a noise-resilient BCH-based fuzzy extractor supporting up to 15% BER. Full article

This study presents a novel framework for digital copyright management that integrates AI-enhanced perceptual hashing, blockchain technology, and digital watermarking to address critical challenges in content protection and verification. Traditional watermarking approaches typically employ content-independent metadata and rely on centralized authorities, introducing risks of tampering and operational inefficiencies. The proposed system utilizes a pre-trained convolutional neural network (CNN) to generate a robust, content-based perceptual hash value, which serves as an unforgeable watermark intrinsically linked to the image content. This hash is embedded as a QR code in the frequency domain and registered on a blockchain, ensuring tamper-proof timestamping and comprehensive traceability. The blockchain infrastructure further enables verification of multiple watermark sequences, thereby clarifying authorship attribution and modification history. Experimental results demonstrate high robustness against common image modifications, strong discriminative capabilities, and effective watermark recovery, supported by decentralized storage via the InterPlanetary File System (IPFS). The framework provides a transparent, secure, and efficient solution for digital rights management, with potential future enhancements including post-quantum cryptography integration. Full article

Loop closure detection is essential for improving the long-term consistency and robustness of simultaneous localization and mapping (SLAM) systems. Existing LiDAR-based loop closure approaches often rely on limited or partial geometric features, restricting their performance in complex environments. To address these limitations, this paper introduces a Density Triangle Descriptor (DTD). The proposed method first extracts keypoints from density images generated from LiDAR point clouds, and then constructs a triangle-based global descriptor that is invariant to rotation and translation, enabling robust structural representation. Furthermore, to enhance local discriminative ability, the neighborhood around each keypoint is modeled as a Gaussian distribution, and a local descriptor is derived from the entropy of its probability distribution. During loop closure detection, candidate matches are first retrieved via hash indexing of triangle edge lengths, followed by entropy-based local verification, and are finally refined by singular value decomposition for accurate pose estimation. Extensive experiments on multiple public datasets demonstrate that compared to STD, the proposed DTD improves the average F1 max score and EP by 18.30% and 20.08%, respectively, while achieving a 50.57% improvement in computational efficiency. Moreover, DTD generalizes well to solid-state LiDAR with non-repetitive scanning patterns, validating its robustness and applicability in complex environments. Full article

Ensuring the integrity of medical images is essential to securing clinical workflows, telemedicine platforms, and healthcare IoT environments. Existing watermarking and reversible data-hiding approaches often modify pixel intensities, reducing diagnostic fidelity, introducing embedding constraints, or causing instability under compression and format conversion. This work proposes a distortion-free, non-embedding authentication framework that leverages the inherent stability of the most significant bit (MSB) patterns in the Non-Region of Interest (NROI) to construct a secure and tamper-sensitive reference for the diagnostic Region of Interest (ROI). The ROI is partitioned into fixed blocks, each producing a 256-bit SHA-256 signature. Instead of embedding this signature, each hash bit is mapped to an NROI pixel whose MSB matches the corresponding bit value, and only the encrypted coordinates of these pixels are stored externally in a secure database. During verification, hashes are recomputed and compared bit-by-bit with the MSB sequence extracted from the referenced NROI coordinates, enabling precise block-level tamper localization without modifying the image. Extensive experiments conducted on MRI (OASIS), X-ray (ChestX-ray14), and CT (CT-ORG) datasets demonstrate the following: (i) perfect zero-distortion fidelity; (ii) stable and deterministic MSB-class mapping with abundant coordinate diversity; (iii) 100% detection of intentional ROI tampering with no false positives across the six clinically relevant manipulation types; and (iv) robustness to common benign Non-ROI operations. The results show that the proposed scheme offers a practical, secure, and computationally lightweight solution for medical image integrity verification in PACS systems, cloud-based archives, and healthcare IoT applications, while avoiding the limitations of embedding-based methods. Full article

The exponential growth of Internet infrastructure and the widespread adoption of smart sensing devices have empowered industrial personnel to conduct remote, real-time data analysis within the Industrial Internet of Things (IIoT) framework. However, transmitting this real-time data over public channels raises significant security and privacy concerns. To prevent unauthorized access, user authentication mechanisms are crucial in the IIoT environment. To mitigate security vulnerabilities within IIoT environments, a novel user authentication and key agreement protocol is proposed. The protocol is designed to restrict service access exclusively to authorized users of designated smart sensing devices. By incorporating cryptographic hash functions, chaotic maps, Physical Unclonable Functions (PUFs), and fuzzy extractors, the protocol enhances security and functional integrity. PUFs provide robust protection against tampering and cloning, while fuzzy extractors facilitate secure biometric verification through the integration of smart cards, passwords, and personal biometrics. Moreover, the protocol accommodates dynamic device enrollment, password and biometric updates, and smart card revocation. A rigorous formal security analysis employing the Real-or-Random (ROR) model was conducted to validate session key security. Complementary informal security analysis was performed to assess resistance to a broad spectrum of attacks. Comparative performance evaluations unequivocally demonstrate the protocol’s superior efficiency and security in comparison to existing benchmarks. Full article

Research on deep neural network (DNN)-based multi-dimensional data visualization has thoroughly explored cross-modal hash retrieval (CMHR) systems, yet their vulnerability to malicious adversarial examples remains evident. Recent work improves the robustness of CMHR networks by augmenting training datasets with adversarial examples. Prior approaches typically formulate the generation of cross-modal adversarial examples as an optimization problem solved through iterative methods. Although effective, such techniques often suffer from slow generation speed, limiting research efficiency. To address this, we propose a generative-based method that enables rapid synthesis of adversarial examples via a carefully designed adversarial generator network. Specifically, we introduce Cross-Gen, a parallel cross-modal framework that constructs semantic triplet data by interacting with the target model through query-based feedback. The generator is optimized using a tailored objective comprising adversarial loss, reconstruction loss, and quantization loss. The experimental results show that Cross-Gen generates adversarial examples significantly faster than iterative methods while achieving competitive attack performance. Full article

This paper presents HV-LIOM (Adaptive Hash-Voxel LiDAR–Inertial Odometry and Mapping), a unified LiDAR–inertial SLAM and autonomous exploration framework for real-time 3D mapping in dynamic, GNSS-denied environments. We propose an adaptive hash-voxel mapping scheme that improves memory efficiency and real-time state estimation by subdividing voxels according to local geometric complexity and point density. To enhance robustness to poor initialization, we introduce a multi-resolution relocalization strategy that enables reliable localization against a prior map under large initial pose errors. A learning-based loop-closure module further detects revisited places and injects global constraints, while global pose-graph optimization maintains long-term map consistency. For autonomous exploration, we integrate a Soft Actor–Critic (SAC) policy that selects informative navigation targets online, improving exploration efficiency in unknown scenes. We evaluate HV-LIOM on public datasets (Hilti and NCLT) and a custom mobile robot platform. Results show that HV-LIOM improves absolute pose accuracy by up to 15.2% over FAST-LIO2 in indoor settings and by 7.6% in large-scale outdoor scenarios. The learned exploration policy achieves comparable or superior area coverage with reduced travel distance and exploration time relative to sampling-based and learning-based baselines. Full article

Because of the advancement of IT, cross-domain environments have emerged where independent clouds with different security policies share data. However, sharing data between clouds with heterogeneous security levels is a challenging task, and most existing access control schemes focus on a single cloud domain. Among various access control models, RBAC is suitable for cross-domain data sharing, but existing RBAC schemes cannot provide strong role privacy and do not support freshness in role verification, so they are vulnerable to replay-based misuse of credentials. In this paper, we propose an RBAC scheme for cross-domain cloud environments based on a hash-chain-augmented zk-SNARK and identity-based signatures. The TA issues IBS-based role signing keys to users, and the user proves, through a zk-SNARK circuit, that there exists a valid role signing key satisfying the access policy without revealing the concrete role information to the CDS. In addition, a synchronized hash chain between the user and the CDS is embedded into the proof so that each proof is tied to the current hash-chain state and any previously used proof fails verification when replayed. We formalize role privacy, replay resistance, and MitM resistance in the cross-domain setting and analyze the proposed scheme by comparing it with Saxena and Alam’s I-RBAC, Xu et al.’s RBAC, MO-RBE, and PE-RBAC. The security analysis shows that the proposed scheme achieves robust role privacy against both the CDS and external attackers and prevents replay and man-in-the-middle attacks. Furthermore, the computational cost evaluation based on the number of pairing, exponentiation, point addition, and hash operations confirms that the verifier-side overhead remains comparable to existing schemes, while the additional prover cost is the price for achieving stronger privacy and security. Therefore, the proposed scheme can be applied to cross-domain cloud systems that require secure and privacy-preserving role verification, such as military, healthcare, and government cloud infrastructures. Full article

In edge computing scenarios, the data generated by distributed devices is characterized by its dispersion, heterogeneity, and privacy sensitivity, posing significant challenges to federated clustering, including high communication overhead, difficulty in adapting to non-IID data, and significant privacy leakage risks. To address these issues, this paper proposes a privacy-enhanced federated k-means clustering algorithm based on locality-sensitive hashing, aiming to mine latent knowledge from multi-source distributed data while ensuring data privacy protection. The core innovation of this algorithm lies in leveraging the distance sensitivity of clustering pairs, which effectively mitigates the non-IID problem while preserving data privacy and achieves global clustering in just a single communication round, significantly enhancing its practicality in communication-constrained environments. Specifically, the algorithm first evaluates local data dispersion at the client side, dynamically generates cluster cardinality based on dispersion, and obtains initial clustering centers through the k-means algorithm. Subsequently, it employs locality-sensitive hashing to encrypt the center points, uploading only the encrypted clustering information and weight data to the server, thereby achieving privacy protection without relying on a trusted server. On the server side, a secondary weighted k-means clustering is performed in the encrypted space to generate hashed global centers. Experimental results on the MNIST and CIFAR-10 datasets demonstrate that this method maintains robust clustering performance under non-IID data distributions. Most crucially, through a strict single-round client-to-server communication protocol, this approach significantly reduces communication overhead, providing a distributed data mining solution that is efficient, adaptable, and privacy-preserving for resource-constrained edge computing environments. Full article

With the emergence of large-scale vision-language pre-training (VLP) models, remote sensing (RS) image–text retrieval is shifting from global representation learning to fine-grained semantic alignment. This review systematically examines two mainstream representation paradigms—real-valued embedding and deep hashing—and analyzes how the evolution of RS datasets influences model capability, including multi-scale robustness, small object discriminability, and temporal semantic understanding. We further dissect three core challenges specific to RS scenarios: multi-scale semantic modeling, small object feature preservation, and multi-temporal reasoning. Representative architectures and technical solutions are reviewed in depth, followed by a critical discussion of their limitations in terms of generalization, evaluation consistency, and reproducibility. We also highlight the growing role of VLP-based models and the dependence of their performance on large-scale, high-quality image–text corpora. Finally, we outline future research directions, including RS-oriented VLP adaptation and unified multi-granularity evaluation frameworks. These insights aim to provide a coherent reference for advancing practical deployment and promoting cross-domain applications of RS image–text retrieval. Full article

As digital images proliferate across open networks, securing them against unauthorized access has become imperative. However, many recent image encryption algorithms are limited by weak chaotic dynamics and inadequate cryptographic design. To overcome these, we propose a new 2D coupling-enhanced cubic hyperchaotic map with exponential parameters (2D-CCHM-EP). By incorporating exponential terms and strengthening interdependence among state variables, the 2D-CCHM-EP exhibits strict local expansiveness, effectively suppresses periodic windows, and achieves robust hyperchaotic behavior, validated both theoretically and numerically. It outperforms several recent chaotic maps in key metrics, yielding significantly higher Lyapunov exponents and Kolmogorov–Sinai entropy, and passes all NIST SP 800-22 randomness tests. Leveraging the 2D-CCHM-EP, we further develop a hierarchical significance-aware multi-image encryption algorithm (MIEA-CPHS). The core of MIEA-CPHS is a hierarchical significance-aware encryption strategy that decomposes input images into high-, medium-, and low-significance layers, which undergo three, two, and one round of vector-level adaptive encryption operations. An SHA-384-based hash of the fused data dynamically generates a 48-bit adaptive control parameter, enhancing plaintext sensitivity and enabling integrity verification. Comprehensive security analyses confirm the exceptional performance of MIEA-CPHS: near-zero inter-pixel correlation (<0.0016), near-ideal Shannon entropy (>7.999), and superior plaintext sensitivity (NPCR $\approx 99.61\%$, UACI $\approx 33.46\%$). Remarkably, the hierarchical design and vectorized operations achieve an average encryption throughput of 87.6152 Mbps, striking an outstanding balance between high security and computational efficiency. This makes MIEA-CPHS highly suitable for modern high-throughput applications such as secure cloud storage and real-time media transmission. Full article