Search Results (129)

Unmanned Aerial Vehicle (UAV) platforms enable flexible and cost-effective vehicle detection for intelligent transportation systems, yet small-scale vehicles in complex aerial scenes pose substantial challenges from extreme scale variations, environmental interference, and single-sensor limitations. We present AMSRDet (Adaptive Multi-Scale Remote Sensing Detector), an adaptive multi-scale detection network fusing infrared (IR) and visible (RGB) modalities for robust UAV-based vehicle detection. Our framework comprises four novel components: (1) a MobileMamba-based dual-stream encoder extracting complementary features via Selective State-Space 2D (SS2D) blocks with linear complexity $O\left(HWC\right)$, achieving 2.1× efficiency improvement over standard Transformers; (2) a Cross-Modal Global Fusion (CMGF) module capturing global dependencies through spatial-channel attention while suppressing modality-specific noise via adaptive gating; (3) a Scale-Coordinate Attention Fusion (SCAF) module integrating multi-scale features via coordinate attention and learned scale-aware weighting, improving small object detection by 2.5 percentage points; and (4) a Separable Dynamic Decoder generating scale-adaptive predictions through content-aware dynamic convolution, reducing computational cost by 48.9% compared to standard DETR decoders. On the DroneVehicle dataset, AMSRDet achieves 45.8% mAP@0.5:0.95 (81.2% mAP@0.5) at 68.3 Frames Per Second (FPS) with 28.6 million (M) parameters and 47.2 Giga Floating Point Operations (GFLOPs), outperforming twenty state-of-the-art detectors including YOLOv12 (+0.7% mAP), DEIM (+0.8% mAP), and Mamba-YOLO (+1.5% mAP). Cross-dataset evaluation on Camera-vehicle yields 52.3% mAP without fine-tuning, demonstrating strong generalization across viewpoints and scenarios. Full article

The proliferation of unmanned aerial vehicles (UAVs) poses escalating security threats across critical infrastructures, necessitating robust real-time detection systems. Existing vision-based methods predominantly rely on single-modality data and exhibit significant performance degradation under challenging scenarios. To address these limitations, we propose DCAM-DETR, a novel multimodal detection framework that fuses RGB and thermal infrared modalities through an enhanced RT-DETR architecture integrated with state space models. Our approach introduces four innovations: (1) a MobileMamba backbone leveraging selective state space models for efficient long-range dependency modeling with linear complexity $\mathcal{O}\left(n\right)$; (2) Cross-Dimensional Attention (CDA) and Cross-Path Attention (CPA) modules capturing intermodal correlations across spatial and channel dimensions; (3) an Adaptive Feature Fusion Module (AFFM) dynamically calibrating multimodal feature contributions; and (4) a Dual-Attention Decoupling Module (DADM) enhancing detection head discrimination for small targets. Experiments on Anti-UAV300 demonstrate state-of-the-art performance with 94.7% mAP@0.5 and 78.3% mAP@0.5:0.95 at 42 FPS. Extended evaluations on FLIR-ADAS and KAIST datasets validate the generalization capacity across diverse scenarios. Full article

Traffic sign detection is crucial for intelligent transportation and autonomous driving, yet faces challenges such as illumination variations, occlusions, and scale changes that impact accuracy. To address these issues, the paper proposes the LSTM-CA-YOLOv11 model. This approach pioneers the integration of a Bi-LSTM (Bi-directional Long-Short Term Memory) into the YOLOv11 backbone network to model spatial-sequence dependencies, thereby enhancing structured feature extraction capabilities. The lightweight CA (Coordinate Attention) module encodes precise positional information by capturing horizontal and vertical features. The MSEF (Multi-Scale Enhancement Fusion) module addresses scale variations through parallel convolutional and pooling branches with adaptive fusion processing. We further introduce the SPP-Plus (Spatial Pyramid Pooling-Plus) module to expand the receptive field while preserving fine details, and employ a focus IoU (Intersection over Union) loss to prioritise challenging samples, thereby improving regression accuracy. On a private dataset comprising 10,231 images, experiments demonstrate that this model achieves a mAP@0.5 of 93.4% and a mAP@0.5:0.95 of 79.5%, representing improvements of 5.3% and 4.7% over the baseline, respectively. Furthermore, the model’s generalisation performance on the public TT100K (Tsinghua-Tencent 100K) dataset surpassed the latest YOLOv13n by 5.3% in mAP@0.5 and 3.9% in mAP@0.5:0.95, demonstrating robust cross-dataset capabilities and exceptional practical deployment feasibility. Full article

In the context of privacy-preserving face recognition systems, entropy plays a crucial role in determining the efficiency and security of computational processes. However, existing schemes often encounter challenges such as inefficiency and high entropy in their computational models. To address these issues, we propose a privacy-preserving face recognition method based on the Face Feature Coding Method (FFCM) and symmetric homomorphic encryption, which reduces computational entropy while enhancing system efficiency and ensuring facial privacy protection. Specifically, to accelerate the matching speed during the authentication phase, we construct an N-ary feature tree using a neural network-based FFCM, significantly improving ciphertext search efficiency. Additionally, during authentication, the server computes the cosine similarity of the matched facial features in ciphertext form using lightweight symmetric homomorphic encryption, minimizing entropy in the computation process and reducing overall system complexity. Security analysis indicates that critical template information remains secure and resilient against both passive and active attacks. Experimental results demonstrate that the facial authentication efficiency with FFCM classification is 4% to 6% higher than recent state-of-the-art solutions. This method provides an efficient, secure, and entropy-aware approach for privacy-preserving face recognition, offering substantial improvements in large-scale applications. Full article

With the exponential growth of digital music, efficiently identifying key music relationship nodes in large-scale music knowledge graphs is crucial for enhancing music recommendation, emotion analysis, and genre classification. To address this challenge, we propose MUSIGAIN, a GATv2-based adaptive framework that combines graph robustness metrics with advanced graph neural network mechanisms for multi-relationship mining in heterogeneous music knowledge graphs. MUSIGAIN tackles three fundamental challenges: the prohibitive computational complexity of exact graph-robustness calculations, the limitations of traditional centrality measures in capturing semantic heterogeneity, and the over-smoothing problem in deep graph neural networks. The framework introduces three key innovations: (1) a layer-wise dynamic skipping mechanism that adaptively controls propagation depth based on third-order embedding stability, reducing computation by 30–40% while preventing over-smoothing; (2) the DiGRAF adaptive activation function that enables node-specific nonlinear transformations to capture semantic heterogeneity across different entity types; and (3) ranking-based optimization supervised by graph robustness metrics, focusing on relative importance ordering rather than absolute value prediction. Experimental results on four real-world music knowledge graphs (POP-MKG, ROCK-MKG, JAZZ-MKG, CLASSICAL-MKG) demonstrate that MUSIGAIN consistently outperforms existing methods in Top-5% node identification accuracy, achieving up to 96.78% while maintaining linear scalability to graphs with hundreds of thousands of nodes. MUSIGAIN provides an efficient, accurate, and interpretable solution for key node identification in complex heterogeneous graphs. Full article

The proliferation of Internet of Things (IoT) devices in financial markets has created distributed ecosystems where cryptocurrency exchanges, trading platforms, and market data providers operate as autonomous edge nodes generating massive volumes of sensitive financial data. Collaborative machine learning across these distributed financial IoT nodes faces fundamental challenges: institutions possess valuable proprietary data but cannot share it directly due to competitive concerns, regulatory constraints, and trust management requirements in decentralized networks. This study presents a privacy-preserving federated learning framework tailored for distributed financial IoT systems, combining differential privacy with Shamir secret sharing to enable secure collaborative intelligence across blockchain-based cryptocurrency trading networks. We implement per-layer gradient clipping and Rényi differential privacy composition to minimize utility loss while maintaining formal privacy guarantees in edge computing scenarios. Using 5.6 million orderbook observations from 11 cryptocurrency pairs collected across distributed exchange nodes, we evaluate three data partitioning strategies simulating realistic heterogeneity patterns in financial IoT deployments. Our experiments reveal that federated edge learning imposes 9–15 percentage point accuracy degradation compared to centralized cloud processing, driven primarily by data distribution heterogeneity across autonomous nodes. Critically, adding differential privacy (ε = 3.0) and cryptographic secret sharing increases this degradation by less than 0.3 percentage points when mechanisms are calibrated appropriately for edge devices. The framework achieves 62–66.5% direction accuracy on cryptocurrency price movements, with confidence-based execution generating 71–137 basis points average profit per trade. These results demonstrate the practical viability of privacy-preserving collaborative intelligence for distributed financial IoT while identifying that the federated optimization gap dominates privacy mechanism costs. Our findings offer architectural insights for designing trustworthy distributed systems in blockchain-enabled financial IoT ecosystems. Full article

Recent work at SCN 2020 by Boyen, Izabachène, and Li introduced a lattice-based key-encapsulation mechanism (KEM) that achieves CCA2-security in the standard model without relying on generic transformations. Their proof, however, leaves a few gaps that prevent a fully rigorous security justification. Building on the same design rationale, we revisit that construction and refine it to obtain a more compact and provably secure KEM under the Learning With Errors assumption. Furthermore, we extend this framework to derive an identity-based variant (IBKEM) whose security is established in the same model. The resulting schemes combine conceptual simplicity with improved efficiency and complete proofs of adaptive-ciphertext security. Full article

We investigate the quantum security of nonce-based encryption under the indistinguishability against quantum chosen-plaintext attacks (IND-qCPA). While classical results establish that IV-based modes such as CBC, CFB, OFB, and CTR achieve IND-qCPA security, we demonstrate that simply replacing the random IV with a nonce undermines both classical and quantum security. To address this, we propose a general transformation from R-IND-qCPA security to N-IND-qCPA security and introduce enhanced variants, namely, CBC2, CFB2, OFB2, and CTR2, that are provably secure in the nonce-based quantum setting. We further show that nonce-based stream cipher encryption inherently satisfies N-IND-qCPA security. These results provide a systematic framework for upgrading IV-based constructions to secure nonce-based counterparts, thereby strengthening practical symmetric encryption against quantum adversaries. Full article

The Enhanced Cipher Block Chaining scheme (eCBC) is an authentication encryption scheme (AE) improved from the CBC encryption scheme. It is shown that eCBC scheme fails to achieve ciphertext integrity (INT-CTXT): the IV is unauthenticated and the tag is a linear XOR of ciphertext hashes, enabling trivial forgeries such as IV substitution, block cancellation, and permutation. Furthermore, the medical image application diagonal block encryption based on eCBC scheme is also insecure. Its deterministic design leaks structural information, breaking confidentiality (IND-CPA). At the same time, it also inherits the forgery weaknesses of eCBC scheme, breaking authenticity. The results highlight that neither eCBC scheme nor its application meet AE security goals. And it is recommended to use standardized AE schemes such as SIV, GCM, or Ascon instead of ad hoc designs. Full article

Geolocating Twitter users from social media data holds significant value in applications such as targeted advertising, disaster response, and social network analysis. However, existing social network-based geolocation methods tend to focus primarily on mention relations while neglecting other critical interactions like retweet relationships. Moreover, effectively integrating diverse social features remains a key challenge, which limits the overall performance of geolocation models. To address these issues, this paper proposes a novel Twitter user geolocation method based on multi-graph feature fusion with a gating mechanism, termed MGFGCN, which fully leverages heterogeneous social network information. Specifically, MGFGCN first constructs separate mention and retweet graphs to capture multi-dimensional user relationships. It then incorporates the Information Gain Ratio (IGR) to select discriminative keywords and generates Term Frequency–Inverse Document Frequency (TF-IDF) features, thereby enhancing the semantic representation of user nodes. Furthermore, to exploit complementary information across different graph structures, we propose a Structure-aware Gated Fusion Mechanism (SGFM) that dynamically captures differences and interactions between nodes from each graph, enabling the effective fusion of node representations into a unified representation for subsequent location inference. Experimental results demonstrate that the proposed method outperforms existing state-of-the-art baselines in the Twitter user geolocation task across two public datasets. Full article

From hieroglyphic writing in ancient Egypt to the post-quantum edge, cryptology is usually seen as an immortal concept that evolves within the enhancement of human civilization. However, modern cryptography primitives try to make revealing ciphered information as tough as possible for attackers. As a sort of enhancement, substitution boxes play an important role in leveraging security, especially for symmetric-based algorithms. The S-box concept is integrated internally into the encryption process for block ciphers and added as a strengthened layer for stream ciphers. Consequently, in-depth analytical considerations are always needed to gather the required information if any S-box wants to be integrated. For this reason, this paper is about providing a scrutiny cryptanalysis for these S-boxes and, more precisely, size ones, since they are not widely investigated. Full article

The widespread emergence of multimodal data on social platforms has presented new opportunities for sentiment analysis. However, previous studies have often overlooked the issue of detail loss during modal interaction fusion. They also exhibit limitations in addressing semantic alignment challenges and the sensitivity of modalities to noise. To enhance analytical accuracy, a novel model named MAHFNet is proposed. The proposed architecture is composed of three main components. Firstly, an attention-guided gated interaction alignment module is developed for modeling the semantic interaction between text and image using a gated network and a cross-modal attention mechanism. Next, a contrastive learning mechanism is introduced to encourage the aggregation of semantically aligned image-text pairs. Subsequently, an intra-modality emotion extraction module is designed to extract local emotional features within each modality. This module serves to compensate for detail loss during interaction fusion. The intra-modal local emotion features and cross-modal interaction features are then fed into a hierarchical gated fusion module, where the local features are fused through a cross-gated mechanism to dynamically adjust the contribution of each modality while suppressing modality-specific noise. Then, the fusion results and cross-modal interaction features are further fused using a multi-scale attention gating module to capture hierarchical dependencies between local and global emotional information, thereby enhancing the model’s ability to perceive and integrate emotional cues across multiple semantic levels. Finally, extensive experiments have been conducted on three public multimodal sentiment datasets, with results demonstrating that the proposed model outperforms existing methods across multiple evaluation metrics. Specifically, on the TumEmo dataset, our model achieves improvements of 2.55% in ACC and 2.63% in F1 score compared to the second-best method. On the HFM dataset, these gains reach 0.56% in ACC and 0.9% in F1 score, respectively. On the MVSA-S dataset, these gains reach 0.03% in ACC and 1.26% in F1 score. These findings collectively validate the overall effectiveness of the proposed model. Full article

In this study, we investigate the application of the direct sampling method (DSM) to identify small dielectric objects in a limited-aperture inverse scattering problem. Unlike previous studies, we consider the bistatic measurement configuration corresponding to the transmitter location and design indicator functions for both a single source and multiple sources, and we convert the unknown measurement data to a fixed nonzero constant. To explain the applicability and limitation of object detection, we demonstrate that the indicator functions can be expressed by an infinite series of Bessel functions, the material properties of the objects, the bistatic angle, and the converted constant. Based on the theoretical results, we explain how the imaging performance of the DSM is influenced by the bistatic angle and the converted constant. In addition, the results of our analyses demonstrate that a smaller bistatic angle enhances the imaging accuracy and that optimal selection of the converted constant is crucial to realize reliable object detection. The results of the numerical simulations obtained using a two-dimensional Fresnel dataset validate the theoretical findings and illustrate the effectiveness and limitations of the designed indicator functions for small objects. Full article

Low-power microcontrollers, wireless sensors, and embedded gateways form the backbone of many Internet of Things (IoT) deployments. However, their limited memory, constrained energy budgets, and lack of standardized firmware make them attractive targets for diverse attacks, including bootloader backdoors, hardcoded keys, unpatched CVE exploits, and code-reuse attacks, while traditional single-layer defenses are insufficient as they often assume abundant resources. This paper presents a Systematic Literature Review (SLR) conducted according to the PRISMA 2020 guidelines, covering 196 peer-reviewed studies on cross-layer security for resource-constrained IoT and Industrial IoT environments, and introduces a four-axis taxonomy—system level, algorithmic paradigm, data granularity, and hardware budget—to structure and compare prior work. At the firmware level, we analyze static analysis, symbolic execution, and machine learning-based binary similarity detection that operate without requiring source code or a full runtime; at the network and behavioral levels, we review lightweight and graph-based intrusion detection systems (IDS), including single-packet authorization, unsupervised anomaly detection, RF spectrum monitoring, and sensor–actuator anomaly analysis bridging cyber-physical security; and at the policy level, we survey identity management, micro-segmentation, and zero-trust enforcement mechanisms supported by blockchain-based authentication and programmable policy enforcement points (PEPs). Our review identifies current strengths, limitations, and open challenges—including scalable firmware reverse engineering, efficient cross-ISA symbolic learning, and practical spectrum anomaly detection under constrained computing environments—and by integrating diverse security layers within a unified taxonomy, this SLR highlights both the state-of-the-art and promising research directions for advancing IoT security. Full article

Accurate and high-resolution spatio-temporal prediction of PM_2.5 concentrations remains a significant challenge for air pollution early warning and prevention. Advanced artificial intelligence (AI) technologies, however, offer promising solutions to this problem. A spatio-temporal prediction model is designed in this study, which is built upon a seq2seq architecture. This model employs an improved graph convolutional neural network to capture spatially dependent features, integrates time-series information through a gated recurrent unit, and incorporates an attention mechanism to achieve PM_2.5 concentration prediction. Benefiting from high-resolution satellite remote sensing data, the regional, multi-step and high-resolution prediction of PM_2.5 concentration in Beijing has been performed. To validate the model’s performance, ablation experiments are conducted, and the model is compared with other advanced prediction models. The experimental results show our proposed Spatio-Temporal Graph Convolutional Network with Attention Mechanism (STGCA) outperforms comparison models in multi-step forecasting, achieving root mean squared error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE) of 4.21, 3.11 and 11.41% for the first step, respectively. For subsequent steps, the model also shows significant improvements. For subsequent steps, the model also shows significant improvements, with RMSE, MAE and MAPE values of 5.08, 3.69 and 13.34% for the second step and 6.54, 4.61 and 16.62% for the third step, respectively. Additionally, STGCA achieves the index of agreement (IA) values of 0.98, 0.97 and 0.95, as well as Theil’s inequality coefficient (TIC) values of 0.06, 0.08 and 0.10 proving its superiority. These results demonstrate that the proposed model offers an efficient technical approach for smart air pollution forecasting and warning in the future. Full article