High Concealment Research Articles

DarkMor: A framework for darknet traffic detection that integrates local and spatial features

The dark web, as an integral part of the multi-layered structure of the internet, provides anonymity and high levels of concealment absent on the surface web. Users can engage in various online activities without leaving any trace, making the dark web a hub for illicit activities, such as drug and weapon trafficking. Consequently, this poses a significant threat to social order and network security. However, due to the high concealment of the dark web, traditional detection methods suffer with insufficient extraction of characteristic information from darknet traffic and inadequate consideration of feature correlations. As a result, the accuracy of these conventional detection methods in detecting the dark web in real network environments is suboptimal. This paper proposes a darknet traffic detection framework called DarkMor to address these challenges. It integrates local and spatial features, automates feature mining and fusion, and models spatial relationship between features to fully exploit their potential. The core components of DarkMor consist of the feature fusion module and the traffic perception module. Using an improved feature tokenizer transformer architecture, the feature fusion module enhances the extraction of local features within high-dimensional feature clusters, effectively combining local feature information with global context. Additionally, the traffic perception module leverages a temporal model that incorporates self-attention mechanisms to learn the spatiotemporal characteristics of fused features, thereby further enhancing the model’s detection. Experimental results demonstrated that DarkMor achieved an accuracy of 97.78% on real network datasets, surpassing the latest cross-modal darknet traffic detection models. Furthermore, DarkMor maintained an accuracy of 97.57% even in network environments with reduced training samples, confirming the feasibility and robustness of the proposed detection framework.

Research on Power Cyber-Physical Cross-Domain Attack Paths Based on Graph Knowledge

Against the background of the construction of new power systems, power generation, transmission, distribution, and dispatching services are open to the outside world for interaction, and the accessibility of attack paths has been significantly enhanced. We are facing cyber-physical cross-domain attacks with the characteristics of strong targeting, high concealment, and cross-space threats. This paper proposes a quantitative analysis method for the influence of power cyber-physical cross-domain attack paths based on graph knowledge. First, a layered attack graph was constructed based on the cross-space and strong coupling characteristics of the power cyber-physical system business and the vertical architecture of network security protection focusing on border protection. The attack graph included cyber-physical cross-domain attacks, control master stations, measurement and control equipment failures, transient stable node disturbances, and other vertices, and achieved a comprehensive depiction of the attack path. Second, the out-degree, in-degree, vertex betweenness, etc., of each vertex in the attack graph were comprehensively considered to calculate the vertex vulnerability, and by defining the cyber-physical coupling degree and edge weights, the risk of each attack path was analyzed in detail. Finally, the IEEE RTS79 and RTS96 node systems were selected, and the impact of risk conduction on the cascading failures of the physical space system under typical attack paths was analyzed using examples, verifying the effectiveness of the proposed method.

Triboelectric based smart ceramic tiles

With the exponential development of the Internet of Things (IoTs), big data, and artificial intelligence (AI), smart home technologies have become crucial to people's lives and the construction of smart cities, driving an increasing demand for distributed sensors. In this work, we have for the first time successfully fabricated smart ceramic tiles (SCTs) that integrate electrodes with ceramic tiles using a layer-by-layer temperature gradient sintering method. These SCTs, which are based on triboelectric nanogenerator (TENG) technology, not only demonstrate high sensitivity and good stability, but also offer the potential for high concealment by adjusting glaze composition and color. Under various motion triggers, the SCTs produced high-discrimination electrical output signals, which proves their potential in behavior recognition. Extreme environmental tests further confirmed the SCTs' superior responsiveness. A wireless security monitoring system for SCT sensing, which was developed using IoT chips, enables remote monitoring via mobile devices. This study not only demonstrates the commercial feasibility of SCTs but also highlights their immense potential for imperceptible monitoring within the smart home domain.

Identification and Analysis of the Geohazards Located in an Alpine Valley Based on Multi-Source Remote Sensing Data.

Geohazards that have developed in densely vegetated alpine gorges exhibit characteristics such as remote occurrence, high concealment, and cascading effects. Utilizing a single remote sensing datum for their identification has limitations, while utilizing multiple remote sensing data obtained based on different sensors can allow comprehensive and accurate identification of geohazards in such areas. This study takes the Latudi River valley, a tributary of the Nujiang River in the Hengduan Mountains, as the research area, and comprehensively uses three techniques of remote sensing: unmanned aerial vehicle (UAV) Light Detection and Ranging (LiDAR), Small Baseline Subset interferometric synthetic aperture radar (SBAS-InSAR), and UAV optical remote sensing. These techniques are applied to comprehensively identify and analyze landslides, rockfalls, and debris flows in the valley. The results show that a total of 32 geohazards were identified, including 18 landslides, 8 rockfalls, and 6 debris flows. These hazards are distributed along the banks of the Latudi River, significantly influenced by rainfall and distribution of water systems, with deformation variables fluctuating with rainfall. The three types of geohazards cause cascading disasters, and exhibit different characteristics in the 0.5 m resolution hillshade map extracted from LiDAR data. UAV LiDAR has advantages in densely vegetated alpine gorges: after the selection of suitable filtering algorithms and parameters of the point cloud, it can obtain detailed terrain and geomorphological information on geohazards. The different remote sensing technologies used in this study can mutually confirm and complement each other, enhancing the capability to identify geohazards and their associated hazard cascades in densely vegetated alpine gorges, thereby providing valuable references for government departments in disaster prevention and reduction work.

Potential Landslide Identification in Baihetan Reservoir Area Based on C-/L-Band Synthetic Aperture Radar Data and Applicability Analysis

The Baihetan reservoir region is characterized by complex geomorphology, significant altitude differences, and rugged terrain. Geological hazards in such areas are often characterized by high concealment, wide distribution, and difficulty in field investigation. Traditional identification techniques are unable to detect and monitor geological hazards on a large scale with high efficiency and accuracy. In recent decades, interferometric synthetic aperture radar (InSAR) techniques, such as small baseline subset InSAR (SBAS-InSAR), have been widely applied to landslide identification. However, due to factors such as vegetation and the degree of landslide deformation, single-band synthetic aperture radar (SAR) still has certain limitations in detecting landslides. In this study, SBAS-InSAR was conducted based on ALOS-2 and Sentinel-1 ascending-descending images covering the Baihetan reservoir region. Deformation identification results were utilized to conduct a statistical analysis of the SAR detection performance and landslide characteristics, and the effect of vegetation on the detection effectiveness of different SAR bands was discussed. The study revealed that when surface vegetation coverage reaches a high degree, the percentage of areas with coverage greater than 0.6 is greater than 95%, the SAR coherence is mainly affected by vegetation thickness; the comparison of the difference change in the average coherence of the C/L bands among the four vegetation types shows that the ratio of the average coherence of the L-bands to the C-bands increases by a factor of three with the increase in thickness and the transition from crops to shrubs and trees. The results showed that the L-band has better detectability than the C-band in alpine-canyon terrain with vegetation coverage and complex vegetation composition. However, considering the high temporal resolution and accessibility of Sentinel-1 SAR data, it is still the main data choice for wide-area identification of landslides in the reservoir area, while other satellite-borne SAR data with different wavelengths and resolutions, such as ALOS, can be used to assist in the identification and monitoring of landslide hazards with significant magnitude of deformations and dense vegetation coverage. Therefore, the combined utilization of multi-band SAR data has the potential to enhance the dependability of landslide identification and monitoring, resulting in more accurate detection results.

Wildlife Real-Time Detection in Complex Forest Scenes Based on YOLOv5s Deep Learning Network

With the progressively deteriorating global ecological environment and the gradual escalation of human activities, the survival of wildlife has been severely impacted. Hence, a rapid, precise, and reliable method for detecting wildlife holds immense significance in safeguarding their existence and monitoring their status. However, due to the rare and concealed nature of wildlife activities, the existing wildlife detection methods face limitations in efficiently extracting features during real-time monitoring in complex forest environments. These models exhibit drawbacks such as slow speed and low accuracy. Therefore, we propose a novel real-time monitoring model called WL-YOLO, which is designed for lightweight wildlife detection in complex forest environments. This model is built upon the deep learning model YOLOv5s. In WL-YOLO, we introduce a novel and lightweight feature extraction module. This module is comprised of a deeply separable convolutional neural network integrated with compression and excitation modules in the backbone network. This design is aimed at reducing the number of model parameters and computational requirements, while simultaneously enhancing the feature representation of the network. Additionally, we introduced a CBAM attention mechanism to enhance the extraction of local key features, resulting in improved performance of WL-YOLO in the natural environment where wildlife has high concealment and complexity. This model achieved a mean accuracy (mAP) value of 97.25%, an F1-score value of 95.65%, and an accuracy value of 95.14%. These results demonstrated that this model outperforms the current mainstream deep learning models. Additionally, compared to the YOLOv5m base model, WL-YOLO reduces the number of parameters by 44.73% and shortens the detection time by 58%. This study offers technical support for detecting and protecting wildlife in intricate environments by introducing a highly efficient and advanced wildlife detection model.

Transmission tower bolt-loosening time–frequency analysis and localization method considering time-varying characteristics

To address the issues of high concealment and difficult positioning of loose bolts in transmission towers, this paper proposes a new method for locating loose bolts in transmission towers. In this method, we divide the vibration response of the transmission tower into low-frequency signals of 2–25 Hz and high-frequency signals of 25–75 Hz. For the low-frequency signals, the single signal component is obtained by adaptive Chirp mode decomposition and uses the general demodulation transformation to deeply denoise the non-modal information. Since frequency characteristics themselves do not contain time information, considering the importance of time information for positioning, we propose a low-frequency time-varying frequency feature that preserves time characteristics based on synchronous wavelet transform and peak search. For the high-frequency signals, we use singular value decomposition to remove signal outliers caused by pulse excitation and eliminate forced vibrations through wavelet packet transform. Without altering its inherent characteristics, this method enables high-frequency time-domain signals to better represent the nonlinear characteristics of transmission towers. Furthermore, based on the powerful capabilities of Timesnet and Transformer in dealing with time series data, we propose a fault diagnosis model, which ultimately achieves the positioning of loose bolts in transmission towers. The bolt node model proves that this approach can better represent the loose bolt characteristics, and the transmission tower model verifies the effectiveness of this approach in locating loose bolts in transmission towers. Finally, bolt-loosening tests were conducted on a 110 kV transmission tower, and the accuracy of the positioning results reached 92.8%, demonstrating the effectiveness and efficiency of this method in practical positioning applications.

Characteristics of groundwater drought and its correlation with meteorological and agricultural drought over the North China Plain based on GRACE

Groundwater drought is distinctive comparing with other droughts, featuring high concealment, long duration, and obvious hysteresis. It may have significant negative effects on agriculture, eco-environment, and social economy sectors. Therefore, investigating the temporal and spatial characteristics of groundwater drought and its driving factors is meaningful for monitoring and assessing the risks of groundwater shortage. In this study, a groundwater drought index based on groundwater storage anomalies (GWSAs) derived from GRACE satellites was developed to detect and analyze drought events. The spatiotemporal variations and trends of historical groundwater droughts from 2002 to 2021 in the North China Plain were evaluated. In addition, the correlations between groundwater drought and meteorological and agricultural drought were analyzed by the detrended cross-correlation analysis. The results indicated that (1) the standardized groundwater storage anomaly index (SGSAI) could better identify and characterize groundwater drought by eliminating the spatial heterogeneity of GWSAs; (2) from 2002 to 2021, the intensity, frequency, duration, and area of groundwater drought showed an increasing trend; (3) groundwater drought had an obvious hysteresis (>9 months) to meteorological drought and the correlation between groundwater drought and meteorological drought increased, while the relationship with agricultural drought decreased; (4) long-term overexploitation of groundwater resources might be the main driving factor for the exacerbating groundwater drought in this area.

A water track laser Doppler velocimeter for use in underwater navigation

Doppler velocity log (DVL) is usually employed to suppress the divergency of the Strapdown Inertial Navigation System (SINS) in underwater navigation, which is not concealable due to high transmittance for acoustic wave in the water. To conduct underwater navigation task with high concealment, a differential laser Doppler velocimeter (LDV) working at water track mode is integrated with SINS in this paper. The developed LDV measures the advance velocity of the underwater carrier with respect to the surrounding water in underwater navigation scenario with advantages of high concealment, high real-time performance, high update rate, light weight, and small dimension. A dynamic river test was conducted to validate the underwater navigation performance of SINS/LDV integrated system. The experimental results show that during the voyage of 4493s and 5271.8 m, the maximum horizontal positioning errors of the proposed SINS/LDV integrated underwater navigation system is 27.8 m and the relative position error is less than 0.6% with respect to total distance. Therefore, the water track LDV is practical to aid SINS in underwater navigation environment.

A Blockchain-Enabled Group Covert Channel against Transaction Forgery

As a decentralized network infrastructure, the data sent to the blockchain are public and temper-evident. The cover of massive normal transactions in a blockchain network is ideal for constructing a stable and reliable covert channel to achieve one-to-many group covert communication. Existing blockchain-based covert communication schemes face challenges in balancing concealment, embedding rate and filtering efficiency, making them unsuitable for direct extension to group scenarios. Adopting a key-leakage scheme can increase the channel capacity while maintaining high concealment from external adversaries. However, it will also expose more knowledge to the receiver. A malicious receiver has the ability to steal a sender’s identity or replay historical transactions to control the entire channel. In this paper, we define the capabilities of malicious receivers in blockchain-based group covert communication scenarios and propose a group covert communication scheme resistant to transaction forgery attacks. Theoretical analysis and experiments prove that our covert transactions do not have any transaction correlativity, ensuring the unique authenticity of the sender’s identity while maintaining supreme concealment compared with the existing schemes. The precision and recall of machine learning detection results can reach 0.57–0.62 (0.5 is the ideal value).

A Frangi filter aided deep learning approach for palaeochannel recognition

SUMMARY In view of the problem of identifying palaeochannels with high concealment and complex geological structures, this paper proposes an intelligent recognition method for palaeochannels based on Frangi filtering and deep learning. The methodology makes use of Maximum Entropy Wigner–Ville Distribution (MEWVD) method to process the original instantaneous amplitude data, which enhance the distinct features of micro palaeochannels in different sensitive frequency bands. The sample 2-D stratigraphic images generated from these data is labelled for the pre-training process of Attention R2U-Net neural network model. Subsequently, Frangi filter is used to identify and enhance the linear structures of river channels in target stratigraphic images, improving the identification effect of the neural network. Finally, RGB data fusion and 3-D visualization carving are performed on the identification data. This method not only eliminates redundant information using the Frangi filter but also proves that the Attention R2U-Net network model structure with attention mechanism and residual convolution structure can effectively improve the segmentation effect for river channels at different scales. Experimental examples show that this method achieves pixel-level feature segmentation of 3-D seismic data for palaeochannels, accurately depicting their shape, width, thickness, flow direction and other features, thus providing support for subsequent well deployment and horizontal well fracturing selection.

Research on the direction perception of cruising copepods by the fish lateral line using pressure difference matrix and residual neural network regression method

Autonomous Underwater Vehicles (AUVs) are high-end marine equipment. In turbid, dimly lit waters that require high concealment, traditional methods struggle to detect targets effectively. Fish, however, can accurately perceive nearby targets using lateral line systems even in harsh environments. This provides inspiration for intelligent detection in AUVs. In this study, the flow field cloud around copepods and visualization of pressure difference matrix are analyzed. A method combining the pressure difference matrix and residual neural network regression is proposed to study how fish lateral lines perceive the direction of cruising copepods. Furthermore, the effects of three key parameters on direction perception are discussed, including perception time scale, initial vertical distance and training angular intervals number. The results indicate that most predicted directions are close to the true directions, with only a small number of misjudgments occurring in the vicinity of the opposite or perpendicular directions to the true direction. Moderate perception time scales (100 ms), shorter vertical distances (2.5 mm), and reasonable training angular intervals number (24 or 36) all lead to lower perception error. This study provides a quantitative analysis of fish lateral line perception mechanism, offering valuable theoretical guidance and technical support for intelligent detection in AUVs.

Polarization-encoded optical secret sharing based on a dielectric metasurface incorporating near-field nanoprinting and far-field holography.

Metasurface encryption with high concealment and resolution is promising for information security. To improve the encryption security, a polarization-encoded secret sharing scheme based on dielectric metasurface by combining the secret sharing method with nanoprinting and holography is proposed. In this encryption scheme, the secret image is split into camouflaged holograms of different polarization channels and shares a total of 24-1 encryption channels. Benefiting from the secret sharing mechanism, the secret image cannot be obtained by decoding the hologram with a single shared key. Specifically, the secret hologram of a specific channel in the far field can be obtained by specifying the optical key, acquiring the near-field nanoprinting image to determine the combination order for the shared key, and decoding using multiple shared keys. The secret sharing encryption scheme can not only enhance the security level of metasurface encryption, but also increase the number of information channels by predefining camouflage information. We believe that it has important potential applications in large-capacity optical encryption and information storage.

Feasibility Study on China-ASEAN Cooperation in the Forewarning Mechanism Against Telecom Fraud

Along with the implementation of the Belt and Road Initiative and the deepening of regional police cooperation, China and ASEAN have jointly reached remarkable achievement on cyberspace security governance, whereas facing numerous new counter-cybercrime challenges at the same time, exemplified by diversified modes and high concealment. Undeniably, China and ASEAN have accumulated abundant experience through formal conferences and informal forums, but the low institutionalization of China-ASEAN cooperation has made it hard to timely and effectively respond to the protean transborder telecom frauds. Forewarning mechanism, as an innovative method to combat telecom fraud, could significantly make up for the deficiency under the current China-ASEAN cooperative system, while enriching the Belt and Road cooperation Initiative, raising the efficiency of controlling cybercrimes, exploiting the advantage of Chinese Internet+ strategy.

Unusual Thermal Quenching of Photoluminescence from an Organic–Inorganic Hybrid [MnBr4]2−‐based Halide Mediated by Crystalline–Crystalline Phase Transition

AbstractThe ability to generate and manipulate photoluminescence (PL) behavior has been of primary importance for applications in information security. Excavating novel optical effects to create more possibilities for information encoding has become a continuous challenge. Herein, we present an unprecedented PL temporary quenching that highly couples with thermodynamic phase transition in a hybrid crystal (DMML)2MnBr4 (DMML=N,N‐dimethylmorpholinium). Such unusual PL behavior originates from the anomalous variation of [MnBr4]2− tetrahedrons that leads to non‐radiation recombination near the phase transition temperature of 340 K. Remarkably, the suitable detectable temperature, narrow response window, high sensitivity, and good cyclability of this PL temporary quenching will endow encryption applications with high concealment, operational flexibility, durability, and commercial popularization. Profited from these attributes, a fire‐new optical encryption model is devised to demonstrate high confidential information security. This unprecedented optical effect would provide new insights and paradigms for the development of luminescent materials to enlighten future information encryption.

Unusual Thermal Quenching of Photoluminescence from an Organic-Inorganic Hybrid [MnBr4 ]2- -based Halide Mediated by Crystalline-Crystalline Phase Transition.

The ability to generate and manipulate photoluminescence (PL) behavior has been of primary importance for applications in information security. Excavating novel optical effects to create more possibilities for information encoding has become a continuous challenge. Herein, we present an unprecedented PL temporary quenching that highly couples with thermodynamic phase transition in a hybrid crystal (DMML)2 MnBr4 (DMML=N,N-dimethylmorpholinium). Such unusual PL behavior originates from the anomalous variation of [MnBr4 ]2- tetrahedrons that leads to non-radiation recombination near the phase transition temperature of 340 K. Remarkably, the suitable detectable temperature, narrow response window, high sensitivity, and good cyclability of this PL temporary quenching will endow encryption applications with high concealment, operational flexibility, durability, and commercial popularization. Profited from these attributes, a fire-new optical encryption model is devised to demonstrate high confidential information security. This unprecedented optical effect would provide new insights and paradigms for the development of luminescent materials to enlighten future information encryption.

E-SAWM: A Semantic Analysis-Based ODF Watermarking Algorithm for Edge Cloud Scenarios

With the growing demand for data sharing file formats in financial applications driven by open banking, the use of the OFD (open fixed-layout document) format has become widespread. However, ensuring data security, traceability, and accountability poses significant challenges. To address these concerns, we propose E-SAWM, a dynamic watermarking service framework designed for edge cloud scenarios. This framework incorporates dynamic watermark information at the edge, allowing for precise tracking of data leakage throughout the data-sharing process. By utilizing semantic analysis, E-SAWM generates highly realistic pseudostatements that exploit the structural characteristics of documents within OFD files. These pseudostatements are strategically distributed to embed redundant bits into the structural documents, ensuring that the watermark remains resistant to removal or complete destruction. Experimental results demonstrate that our algorithm has a minimal impact on the original file size, with the watermarked text occupying less than 15%, indicating a high capacity for carrying the watermark. Additionally, compared to existing explicit watermarking schemes for OFD files based on annotation structure, our proposed watermarking scheme is suitable for the technical requirements of complex dynamic watermarking in edge cloud scenario deployment. It effectively overcomes vulnerabilities associated with easy deletion and tampering, providing high concealment and robustness.

Prediction of Impulsive Aggression Based on Video Images.

In response to the subjectivity, low accuracy, and high concealment of existing attack behavior prediction methods, a video-based impulsive aggression prediction method that integrates physiological parameters and facial expression information is proposed. This method uses imaging equipment to capture video and facial expression information containing the subject's face and uses imaging photoplethysmography (IPPG) technology to obtain the subject's heart rate variability parameters. Meanwhile, the ResNet-34 expression recognition model was constructed to obtain the subject's facial expression information. Based on the random forest classification model, the physiological parameters and facial expression information obtained are used to predict individual impulsive aggression. Finally, an impulsive aggression induction experiment was designed to verify the method. The experimental results show that the accuracy of this method for predicting the presence or absence of impulsive aggression was 89.39%. This method proves the feasibility of applying physiological parameters and facial expression information to predict impulsive aggression. This article has important theoretical and practical value for exploring new impulsive aggression prediction methods. It also has significance in safety monitoring in special and public places such as prisons and rehabilitation centers.

Optical image conversion and encryption based on structured light illumination and a diffractive neural network.

In this paper, an optical image encryption method is proposed based on structured light illumination and a diffractive neural network (DNN), which can realize conversion between different images. With the use of the structured phase mask (SPM) in the iterative phase retrieval algorithm, a plaintext image is encoded into a DNN composed of multiple phase-only masks (POMs) and ciphertext. It is worth noting that ciphertext is a visible image such that the conversion of one image to another is achieved, leading to high concealment of the proposed optical image encryption method. In addition, the wavelength of the illuminating light, all Fresnel diffraction distances, the optical parameters of the adopted SPM such as focal length and topological charge number, as well as all POMs in the DNN are all considered as security keys in the decryption process, contributing to a large key space and high level of security. Numerical simulations are performed to demonstrate the feasibility of the proposed method, and simulation results show that it exhibits high feasibility and safety as well as strong robustness.

An Automatic Graphic Pattern Generation Algorithm and Its Application to the Multipurpose Camouflage Pattern Design.

Graphic patterns are usually drawn manually by graphic designers. Although many methods have been developed to computerize the creation process of graphic patterns, most of them solely provide some facilitating tools for the designers and could not propose an automatic procedure. This article proposes a fully automatic graphic pattern generation (AGPG) model that performs the entire pattern generation process without any human interference. We then customize the proposed model for camouflage pattern design. Most of the existing camouflage pattern creation methods consider only one or a few background images. Since the objects move and their backgrounds may vary significantly, it is essential to generate multipurpose camouflage patterns with appropriate performance in various backgrounds. The previously proposed methods are also heavily dependent on the existing patterns to produce new ones and could not create novel structures in their generated patterns. Our model is equipped with a novel creative drawing engine that can create a wide variety of new graphical structures without using any existing pattern. The drawing module in our model is controlled by several parameters tuned for the desired task employing an evolutionary strategy-based algorithm. The proposed method has no limits for the number of background images and creates the camouflage patterns appropriate for any number of provided images. The experimental results show that the AGPG method can create novel multipurpose camouflage patterns automatically with high concealment capabilities.