Search Results (105)

We present GANimate, a lightweight method for animating talking faces that leverages recent advances in latent-space manipulation of Generative Adversarial Networks (GANs). Unlike existing approaches based on computationally intensive diffusion models, transformers, or complex 3DMM representations, which are impractical for mobile and other low-resource edge devices due to high memory and compute demands, GANimate is designed for efficient operation on low-memory, low-compute edge devices. The model operates on 2D lip landmarks extracted from standard mobile vision-sensor inputs and requires no pre-training, making it easily integrable with any lip-landmark generator. Through an optimization process in the GAN feature latent space, these landmarks act as geometric constraints to animate a static portrait, producing realistic and expressive lip movements. To maintain stability and visual coherence across frames, we employ a Kalman filter to detect and track lip landmarks during video synthesis, enabling adaptive refinement and improved temporal consistency. The result is a compact and modular framework that bridges the gap between performance and accessibility in talking face synthesis, delivering high-quality and stable animations with minimal computational overhead. GANimate represents an important step toward lifelike, real-time avatars suitable for sensor-enabled and mobile human–computer interaction. Full article

Rebar binding is a labor-intensive and low-efficiency process in the production of reinforced concrete prefabricated components, in which consistent binding quality is difficult to guarantee. To address the engineering challenges faced by rebar binding robots in complex construction environments—particularly in terms of binding-point recognition accuracy, real-time performance, and manipulator path planning efficiency—this paper presents an integrated method for binding-point recognition, localization, and binding path planning tailored to rebar binding tasks. First, based on the YOLOv8n-pose architecture, a lightweight rebar binding-point recognition and localization model, termed YOLOv8n-pose-Binding, is developed by introducing multi-scale Ghost convolution structures and an adaptive threshold focal loss. The proposed model improves keypoint detection accuracy and real-time performance while effectively reducing computational complexity, making it suitable for deployment on resource-constrained mobile robotic platforms. Second, a dedicated target coordinate system for rebar binding points is constructed to enable accurate pose estimation in the manipulator base frame. Furthermore, considering the non-uniform obstacle distribution in rebar mesh environments and the high-dimensional motion characteristics of robotic manipulators, systematic improvements are introduced to the RRT-Connect framework from the perspectives of sampling strategies, tree expansion, node reconnection, and path pruning, resulting in an improved RRT-Connect path planning algorithm. Simulation and experimental results demonstrate that, while maintaining favorable real-time performance, the proposed method achieves stable improvements in recognition accuracy and inference efficiency compared with the baseline YOLOv8n-pose model. In addition, the improved RRT-Connect algorithm exhibits superior engineering performance in terms of path planning efficiency and path quality, providing a deployable technical solution for automated rebar binding operations. Full article

Viticulture is facing growing economic and environmental pressures that demand a transition toward intelligent and autonomous crop management systems. Phytopathologies remain one of the most critical threats, causing substantial yield losses and reducing grape quality, while regulatory restrictions on agrochemicals and sustainability goals are driving the development of precision agriculture solutions. In this context, early disease detection is crucial; however, current visual inspection methods are hindered by subjectivity, cost, and delayed symptom recognition. This study presents a fully autonomous robotic platform developed within the Agrimet project, enabling continuous, high-frequency monitoring in vineyard environments. The system integrates a tracked mobility base, multimodal sensing using RGB-D and thermal cameras, an AI-based perception framework for leaf localisation, and a compliant six-axis manipulator for biological sampling. A custom control architecture bridges standard autopilot PWM signals with industrial CANopen motor drivers, achieving seamless coordination among all subsystems. Field validation in a Sicilian vineyard demonstrated the platform’s capability to navigate autonomously, acquire multimodal data, and perform precise georeferenced sampling under unstructured conditions. The results confirm the feasibility of holistic robotic systems as a key enabler for sustainable, data-driven viticulture and early disease management. The YOLOv10s detection model achieved good precision and F1-score for leaf detection, while the integrated Kalman filtering visual servoing system demonstrated low spatial tolerance under field conditions despite foliage sway and vibrations. Full article

Intensive Care Units (ICUs) face unprecedented challenges in resource allocation, particularly during health crises in which algorithmic systems may be exposed to adversarial manipulation. A transformer-based expert system, ICU-Transformer, is presented to optimize resource allocation across 200 ICUs in Physionet while maintaining robustness against data poisoning attacks. The framework incorporates a Robust Multi-Head Attention mechanism that achieves an AUC-ROC of 0.891 in mortality prediction under 20% data contamination, outperforming conventional baselines. The system is trained and evaluated using data from the MIMIC-IV and eICU Collaborative Research Database and is deployed to manage more than 50,000 ICU admissions annually. A Resource Optimization Engine (ROE) is introduced to dynamically allocate ventilators, Extracorporeal Membrane Oxygenation (ECMO) machines, and specialized clinical staff based on predicted deterioration risk, resulting in an 18% reduction in preventable deaths. A Surge Capacity Planner (SCP) is further employed to simulate disaster scenarios and optimize cross-hospital resource distribution. Deployment across the Physionet ICU Network demonstrates improvements, including a 2.1-day reduction in average ICU bed turnover time, a 31% decrease in unnecessary admissions, and an estimated USD 142 million in annual operational savings. During the observation period, 234 algorithmic manipulation attempts were detected, with targeted disparities identified and mitigated through enhanced auditing protocols. Full article

Blockchain networks face a critical but understudied threat: wave attacks that exploit difficulty adjustment algorithms through strategic mining participation. Adversaries cyclically withdraw and re-enter mining to create oscillations that degrade network liveness and destabilize honest miners’ revenue. We present the first production-ready framework that maintains network responsiveness while enabling robust, post hoc threat detection. The framework employs a statistically rigorous pipeline featuring controller-aligned anomaly detection, transitive collusion grouping via union-find, and Benjamini–Hochberg False Discovery Rate control. We formally prove the economic viability of this architecture: when penalties on unvested rewards are enabled by governance, wave attacks become asymptotically unprofitable for rational adversaries. Evaluated on a 128-node distributed testbed simulating Bitcoin, Ethereum Classic, and Monacoin networks over 30 independent runs, our framework achieves 92.7% F1-score in detecting attacks, significantly outperforming baseline methods (74.7%). This work provides a complete, theoretically-grounded solution for securing proof-of-work blockchains against difficulty manipulation, forming the foundation for the adaptive AI-driven enhancements presented in our companion paper (Part II). Full article

Graph-based Recommender Systems (GRSs) model complex user–item relationships. They offer improved accuracy and personalization in recommendations compared to traditional models. However, GRSs also face severe challenges from novel poisoning attacks. Attackers often manipulate GRS graph structures by injecting attack users and their interaction data. This leads to misleading recommendations. Existing detection methods lack the ability to identify such attacks targeting graph-based systems. To address this, we propose AutoDAP, a novel autoencoder-based detection method for poisoning attacks in GRSs. AutoDAP first extracts key statistical features from user interaction data. It fuses them with original interaction information. Then, an autoencoder architecture processes this data. The encoder extracts deep features and connects to an output layer for classification prediction probabilities. The decoder reconstructs graph structure features. By jointly optimizing classification and reconstruction losses, AutoDAP effectively integrates supervised and unsupervised signals. This enhances the detection of attack users. Evaluations on the MovieLens-10M dataset against various poisoning attacks, and on the Amazon dataset with real attack data, demonstrate AutoDAP’s superiority. It outperforms several representative baseline methods in both simulated (MovieLens) and real-world (Amazon) attack scenarios, demonstrating its effectiveness and robustness. Full article

Unmanned Aerial Vehicles (UAVs) are increasingly being used in critical infrastructure, defense, and civilian applications, and face new cybersecurity threats. In this work, we present a novel hybrid deep learning architecture that combines Mamba, Kolmogorov-Arnold Networks (KAN), and Liquid Neural Networks for real-time cyberattack detection in UAV systems. The proposed Mamba-KAN-Liquid (MKL) model integrates Mamba’s selective state-space mechanism for temporal dependency modeling, KAN’s learnable activation functions for feature representation, and Liquid networks’ dynamic adaptation capabilities for real-time anomaly detection. Extensive evaluations on CIC-IDS2017, CSE-CIC-IDS2018, and synthetic UAV telemetry datasets demonstrate that our model achieves detection rates exceeding 95% across six different attack scenarios, including GPS spoofing (97.3%), network jamming (95.8%), man-in-the-middle attacks (96.2%), sensor manipulation (94.7%), DDoS (98.1%), and zero-day attacks (89.4%). The model meets real-time processing requirements with an average inference time of 47.3 ms for a sample batch size of 32, making it suitable for practical deployment on resource-constrained UAV platforms. Full article

Background: This study aimed to evaluate the agreement among different evaluators in assessing smile esthetics from frontal-view photographs of the lower third of the face during smiling, and afterwards to determine thresholds of perceptibility and acceptability of tooth and gingival shade changes on a single modified digital photograph. Methods: Sixty photographs of the lower third of the face of individuals with pleasing smiles were obtained. Evaluator groups included laypeople, general dentists, and specialists in periodontology, orthodontics, and prosthodontics. Esthetic assessment was performed using seven items from the Orofacial Esthetic Scale (OES). One photograph was digitally manipulated by altering the shade of the first maxillary incisor and the gingiva of the right maxillary second incisor. Perceptibility thresholds and acceptability of these modifications were assessed by all evaluator groups. Results: Specialists in periodontology and prosthodontics, although rating 60 photographs as more esthetically pleasing, detected changes in tooth and gingival color earlier and judged such deviations as unacceptable sooner than general dentists and laypeople, particularly for shifts in lighter shades. Laypeople noticed color changes later but classified them as unacceptable almost immediately showing greater tolerance for lighter shades. Conclusions: The study shows that laypeople prioritize brighter tooth shades, whereas dental specialists value a more natural appearance. Specialists’ early detection of subtle shade changes and discerning judgments reflects their clinical training and awareness of the challenges in achieving perfect esthetics. In contrast, laypeople, seeking bright teeth influenced by social esthetic norms, noticed changes later but judged them as unacceptable more quickly. Full article

As the development of autonomous vehicles (AVs) progresses, new seating arrangements are emerging. Face-to-face seating is common in SAE L4 AV concepts and is intended to facilitate social interaction during autonomous driving, enabling previously unfeasible non-driving related tasks (NDRTs). However, this is countered by the unpopularity of rearward seating orientations, which is particularly pronounced in cars. In order to develop countermeasures to address this unpopularity, a deeper understanding of the underlying mechanisms is required. This study validates a model that predicts the acceptance of AVs and takes seating orientation into account. To this end, a study with N = 46 participants was conducted to investigate the influence of seating orientation on AV acceptance and related factors such as transparency, trust, and motion sickness. Additionally, internal human–machine interfaces (iHMIs) were evaluated in regard to their ability to compensate for the disadvantages of a rearward seating orientation. To achieve a realistic implementation of a fully functional SAE L4 AV, an experimental vehicle was equipped with a steering and pedal robot, performing self-driven journeys on a test track. The iHMIs provided information about upcoming maneuvers and detected road users. While engaged in a social NDRT, participants experienced a total of six journeys. Seating orientation and iHMI visualization were manipulated between journeys. Rearward-facing passengers showed lower levels of trust and higher levels of motion sickness than forward-facing passengers. However, the iHMIs had no effect on acceptance or related factors. Based on these findings, an updated version of the model is proposed, showing that rearward-facing passengers in autonomous vehicles pose a particular challenge for trust calibration and motion sickness mitigation. During NDRTs, iHMIs which depend on the attention of AV occupants for information transfer appear to be ineffective. Implications for future research and design of iHMIs to address this challenge are discussed. Full article

As crucial transportation hubs and economic nodes, the underwater security and infrastructure maintenance of harbors are of paramount importance. Harbors are characterized by high vessel traffic and complex underwater environments, where traditional underwater inspection methods, such as diver operations, face challenges of low efficiency, high risk, and limited operational range. This paper introduces a collaborative survey and disposal system that integrates a deformable unmanned surface vehicle (USV) with a lightweight remotely operated vehicle (ROV). The USV is equipped with a side-scan sonar (SSS) and a multibeam echo sounder (MBES), enabling rapid, large-area searches and seabed topographic mapping. The ROV, equipped with an optical camera system, forward-looking sonar (FLS), and a manipulator, is tasked with conducting close-range, detailed observations to confirm and dispose of abnormal objects identified by the USV. Field trials were conducted at an island harbor in the South China Sea, where simulated underwater objects, including an iron drum, a plastic drum, and a rubber tire, were deployed. The results demonstrate that the USV-ROV collaborative system effectively meets the demands for underwater environmental measurement, object localization, identification, and disposal in complex harbor environments. The USV acquired high-resolution (0.5 m × 0.5 m) three-dimensional topographic data of the harbor, effectively revealing its topographical features. The SSS accurately localized and preliminarily identified all deployed simulated objects, revealing their acoustic characteristics. Repeated surveys revealed a maximum positioning deviation of 2.2 m. The lightweight ROV confirmed the status and location of the simulated objects using an optical camera and an underwater positioning system, with a maximum deviation of 3.2 m when compared to the SSS locations. The study highlights the limitations of using either vehicle alone. The USV survey could not precisely confirm the attributes of the objects, whereas a full-area search of 0.36 km² by the ROV alone would take approximately 20 h. In contrast, the USV-ROV collaborative model reduced the total time to detect all objects to 9 h, improving efficiency by 55%. This research offers an efficient, reliable, and economical practical solution for applications such as underwater security, topographic mapping, infrastructure inspection, and channel dredging in harbor environments. Full article

In recent years, the proliferation of forged videos, known as deepfakes, has escalated significantly, primarily due to advancements in technologies such as Generative Adversarial Networks (GANs), diffusion models, and Vision Language Models (VLMs). These deepfakes present substantial risks, threatening political stability, facilitating celebrity impersonation, and enabling tampering with evidence. As the sophistication of deepfake technology increases, detecting these manipulated videos becomes increasingly challenging. Most of the existing deepfake detection methods use Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), or Vision Transformers (ViTs), achieving strong accuracy but exhibiting high computational demands. This highlights the need for a lightweight yet effective pipeline for real-time and resource-limited scenarios. This study introduces a lightweight deep learning model for deepfake detection in order to address this emerging threat. The model incorporates three integral components: MobileNet for feature extraction, a Convolutional Block Attention Module (CBAM) for feature enhancement, and a Gated Recurrent Unit (GRU) for temporal analysis. Additionally, a pre-trained Multi-Task Cascaded Convolutional Network (MTCNN) is utilized for face detection and cropping. The model is evaluated using the Deepfake Detection Challenge (DFDC) and Celeb-DF v2 datasets, demonstrating impressive performance, with 98.2% accuracy and a 99.0% F1-score on Celeb-DF v2 and 95.0% accuracy and a 97.2% F1-score on DFDC, achieving a commendable balance between simplicity and effectiveness. Full article

This study presents a novel, fully passive radiofrequency (RF)-based localization system designed to detect the position of a robotic hand on a flat surface within its tactile range, particularly in scenarios where other sensing systems may face limitations. The system employs U-shaped, chipless resonator tags printed on the surface using a customized conductive ink, together with a coplanar RF probe integrated into the robotic hand, to determine position through impedance variations. Unlike conventional approaches, the proposed method provides a compact, low-cost, and robust solution that is resilient to variations in lighting, dust, and other environmental conditions. The resonator tags are arranged in a structured grid inspired by a Sudoku pattern, enabling both position and orientation detection in the near-field region. The system is fabricated on 3D-printed flexible substrates using a flexible and stretchable conductive ink, and its performance is validated through both electromagnetic simulations and experimental measurements. The results confirm that the proposed approach enables accurate and repeatable two-dimensional localization of the robotic hand under various configurations. This work introduces a scalable, high-precision, and vision-independent sensing platform with strong potential for robotic manipulation in challenging environments. Full article

The development of artificial intelligence has inevitably led to the growth of deepfake images, videos, human voices, etc. Deepfake detection is mandatory, especially when used for unethical and illegal purposes. This study presents a novel approach to image deepfake detection by introducing the Custom-Made Facial Recognition Algorithm (CMFRA), which employs four distinct features to differentiate between authentic and deepfake images. The proposed method combines facial landmark detection with advanced statistical analysis, integrating mean Mahalanobis distance and three head pose coordinates (yaw, pitch, and roll). The landmarks are extracted using the Google Vision API. This multi-feature approach assesses facial structure and orientation, capturing subtle inconsistencies indicative of deepfake manipulations. A key innovation of this work is introducing the mean Mahalanobis distance as a core feature for quantifying spatial relationships between facial landmarks. The research also emphasizes anomaly analysis by focusing solely on authentic facial data to establish a baseline for natural facial characteristics. The anomaly detection model recognizes when a face is modified without extensive training on deepfake samples. The process is implemented by analyzing deviations from this established pattern. The CMFRA demonstrated a detection accuracy of 90%. The proposed algorithm distinguishes between authentic and deepfake images under varied conditions. Full article

As face forgery techniques, particularly the DeepFake method, progress, the imperative for effective detection of manipulations that enable hyper-realistic facial representations to mitigate security threats is emphasized. Current spatial domain approaches commonly encounter difficulties in generalizing across various forgery methods and compression artifacts, whereas frequency-based analyses exhibit promise in identifying nuanced local cues; however, the absence of global contexts impedes the capacity of detection methods to improve generalization. This study introduces a hybrid architecture that integrates Efficient-ViT and multi-level wavelet transform to dynamically merge spatial and frequency features through a dynamic adaptive multi-branch attention (DAMA) mechanism, thereby improving the deep interaction between the two modalities. We innovatively devise a joint loss function and a training strategy to address the imbalanced data issue and improve the training process. Experimental results on the FaceForensics++ and Celeb-DF (V2) have validated the effectiveness of our approach, attaining 97.07% accuracy in intra-dataset evaluations and a 74.7% AUC score in cross-dataset assessments, surpassing our baseline Efficient-ViT by 14.1% and 7.7%, respectively. The findings indicate that our approach excels in generalization across various datasets and methodologies, while also effectively minimizing feature redundancy through an innovative orthogonal loss that regularizes the feature space, as evidenced by the ablation study and parameter analysis. Full article

Modern cloud-based Internet of Things (IoT) infrastructures face increasingly sophisticated and diverse cyber threats that challenge traditional detection systems in terms of scalability, adaptability, and explainability. In this paper, we present (H-DIR)², a hybrid entropy-based framework designed to detect and mitigate anomalies in large-scale heterogeneous networks. The framework combines Shannon entropy analysis with Associated Random Neural Networks (ARNNs) and integrates semantic reasoning through RDF/SPARQL, all embedded within a distributed Apache Spark 3.5.0 pipeline. We validate (H-DIR)² across three critical attack scenarios—SYN Flood (TCP), DAO-DIO (RPL), and NTP amplification (UDP)—using real-world datasets. The system achieves a mean detection latency of 247 ms and an AUC of 0.978 for SYN floods. For DAO-DIO manipulations, it increases the packet delivery ratio from 81.2% to 96.4% (p < 0.01), and for NTP amplification, it reduces the peak load by 88%. The framework achieves vertical scalability across millions of endpoints and horizontal scalability on datasets exceeding 10 TB. All code, datasets, and Docker images are provided to ensure full reproducibility. By coupling adaptive neural inference with semantic explainability, (H-DIR)² offers a transparent and scalable solution for cloud–IoT cybersecurity, establishing a robust baseline for future developments in edge-aware and zero-day threat detection. Full article