Search

This paper proposes an innovative approach capitalized on the distinctive characteristics of command and control (C&C) beacons, namely, time intervals and frequency between consecutive unique connections, to compress the network flow dataset. While previous studies on the same matter used single technique, we propose a multi-technique approach for efficient detection of DoH tunnels. We use a baseline public dataset, CIRA-CIC-DoHBrw-2020, containing over a million network flow properties and statistical features of DoH, tunnels, benign DoH and normal browsing (HTTPS) traffic. Each sample is represented by 33 features with a timestamp. Our methodology combines star graph and bar plot visualizations with supervised and unsupervised learning techniques. The approach underscores the importance of C&C beacon characteristic features in compressing a dataset and reducing a flow dimension while enabling efficient detection of DoH tunnels. Through compression, the original dataset size and dimensions are reduced by approximately 95 % and 94 % respectively. For supervised learning, RF emerges as the top-performing algorithm, attaining precision and recall scores of 100% each, with speed increase of ≈ 6796 times faster in training and ≈ 55 in testing. For anomaly detection models, OCSVM emerges as the most suitable choice for this purpose, with precision (88.89) and recall (100). Star graph and bar graph models also show a clear difference between normal traffic and DoH tunnels. The reduction in flow sample size and dimension, while maintaining accuracy, holds promise for edge networks with constrained resources and aids security analysts in interpreting complex ML models to identify Indicators of Compromise (IoC). [ABSTRACT FROM AUTHOR]

The failure threshold of a product is not always constant when affected by random shocks. Thus, this paper establishes a reliability model that combines dynamic failure threshold and self-healing characteristics, which are subjected to the competing failure process. Soft failure is caused by degradation exceeding the soft failure threshold, and hard failure occurs because of random shocks. Degradation consists of natural degradation and a degradation increment caused by shocks. The failure thresholds and degradation rate will also be affected by random shocks. Moreover, the self-healing characteristics in the degradation process, together with the degradation increment, will affect the whole degradation process. When the random shock arrives, the soft and hard failure thresholds will change simultaneously. Based on the above factors, the corresponding analytical expressions of reliability models under different shock models are derived. To confirm the effectiveness of the proposed model, an example of micro-engine is used to verify the constructed reliability model. The influences of self-healing and dynamic thresholds in micro-engines on reliability are studied. The effects of self-healing and thresholds on the models are analyzed, which can provide study basis for the maintenance and replacement of product. [ABSTRACT FROM AUTHOR]

As a crucial task for disease diagnosis, existing semi-supervised segmentation approaches process labeled and unlabeled data separately, ignoring the relationships between them, thereby limiting further performance improvements. In this work, we introduce a transformer-based multi-task framework that concurrently leverages both labeled and unlabeled volumes by encoding shared representation patterns. We first integrate transformers into YOLOv5 to enhance segmentation capabilities and adopt a multi-task approach spanning shadow region detection and boundary localization. Subsequently, we leverage the mean teacher model to simultaneously learn from labeled and unlabeled inputs alongside orthogonal view representations, enabling our approach to harness all available annotations. Our network can improve the learning ability and attain superior performance. Extensive experiments demonstrate that the transformer-powered architecture encodes robust inter-sample relationships, unlocking substantial performance gains by capturing shared information between labeled and unlabeled data. By treating both data types concurrently and encoding their shared patterns, our framework addresses the limitations of existing semi-supervised approaches, leading to improved segmentation accuracy and robustness. [ABSTRACT FROM AUTHOR]

Featured Application: This work investigates the application of transformers for general medical image segmentation tasks. The key future directions involve developing unified AI-based system for integrated diagnosis, interactive segmentation to enable human. Automatic image segmentation is vital for the computer-aided determination of treatment directions, particularly in terms of labelling lesions or infected areas. However, the manual labelling of disease regions is inconsistent and a time-consuming assignment. Meanwhile, radiologists' comments are exceedingly subjective, regularly impacted by personal clinical encounters. To address these issues, we proposed a transformer learning strategy to automatically recognize infected areas in medical images. We firstly utilize a parallel partial decoder to aggregate high-level features and then generate a global feature map. Explicit edge attention and implicit reverse attention are applied to demonstrate boundaries and enhance their expression. Additionally, to alleviate the need for extensive labeled data, we propose a segmentation network combining propagation and transformer architectures that requires only a small amount of labeled data while leveraging fundamentally unlabeled images. The attention mechanisms are integrated within convolutional networks, keeping their global structures intact. Standalone transformers connected straightforwardly and receiving image patches can also achieve impressive segmentation performance. Our network enhanced the learning ability and attained a higher quality execution. We conducted a variety of ablation studies to demonstrate the adequacy of each modelling component. Experiments conducted across various medical imaging modalities illustrate that our model beats the most popular segmentation models. The comprehensive results also show that our transformer architecture surpasses established frameworks in accuracy while better preserving the natural variations in anatomy. Both quantitatively and qualitatively, our model achieves a higher overlap with ground truth segmentations and improved boundary adhesion. [ABSTRACT FROM AUTHOR]

Objective: Accurate vocal cord leukoplakia classification is instructive for clinical diagnosis and surgical treatment. This article introduces a reliable very deep Siamese network for accurate vocal cord leukoplakia classification. Study Design: A study of a classification network based on a retrospective database. Setting: Academic university and hospital. Methods: The white light image datasets of vocal cord leukoplakia used in this article were classified into 6 classes: normal tissues, inflammatory keratosis, mild dysplasia, moderate dysplasia, severe dysplasia, and squamous cell carcinoma. The classification performance was assessed by comparing it with 6 classical deep learning models, including AlexNet, VGG Net, Google Inception, ResNet, DenseNet, and Vision Transformer. Results: Experiments show the superior classification performance of our proposed network compared to state‐of‐the‐art methods. The overall accuracy is 0.9756. The values of sensitivity and specificity are very high as well. The confusion matrix provides information for the 6‐class classification task and demonstrates the superiority of our proposed network. Conclusion: Our very deep Siamese network can provide accurate classification results of vocal cord leukoplakia, which facilitates early detection, clinical diagnosis, and surgical treatment. The excellent performance obtained in white light images can reduce the cost for patients, especially those living in developing countries. [ABSTRACT FROM AUTHOR]

The traditional safety distance model based on the braking process is inadequate for scenarios where the adhesion coefficient varies. This research presents a safety distance model that takes into account the real-time fluctuations in the adhesion coefficient during the braking process. The proposed safety distance model is the basis for a three-level control strategy aimed at ensuring the safety and stability of the car-following process. A simulation is conducted to model the variation of the road's adhesion coefficient during car braking. The experimental results, obtained for various initial adhesion coefficients and speeds, demonstrate that the precision of the safety distance calculated is improved by a minimum of 14.99% when compared to the traditional safety distance. Furthermore, the simulation results of the car-following process of a motorcade consisting of five cars provide evidence of the safety and stability of the suggested model. [ABSTRACT FROM AUTHOR]

Background: Accurate vocal cord leukoplakia classification is critical for the individualized treatment and early detection of laryngeal cancer. Numerous deep learning techniques have been proposed, but it is unclear how to select one to apply in the laryngeal tasks. This article introduces and reliably evaluates existing deep learning models for vocal cord leukoplakia classification. Methods: We created white light and narrow band imaging (NBI) image datasets of vocal cord leukoplakia which were classified into six classes: normal tissues (NT), inflammatory keratosis (IK), mild dysplasia (MiD), moderate dysplasia (MoD), severe dysplasia (SD), and squamous cell carcinoma (SCC). Vocal cord leukoplakia classification was performed using six classical deep learning models, AlexNet, VGG, Google Inception, ResNet, DenseNet, and Vision Transformer. Results: GoogLeNet (i.e., Google Inception V1), DenseNet‐121, and ResNet‐152 perform excellent classification. The highest overall accuracy of white light image classification is 0.9583, while the highest overall accuracy of NBI image classification is 0.9478. These three neural networks all provide very high sensitivity, specificity, and precision values. Conclusion: GoogLeNet, ResNet, and DenseNet can provide accurate pathological classification of vocal cord leukoplakia. It facilitates early diagnosis, providing judgment on conservative treatment or surgical treatment of different degrees, and reducing the burden on endoscopists. [ABSTRACT FROM AUTHOR]

The degradation process analysis is the basis of the system reliability assessment. Too few degradation samples will affect the accuracy of the reliability analysis. So, it is necessary to expand the degradation data and construct the degradation prediction model. This paper proposes an SVAE‐GRU‐based degradation generation and prediction model to handle the issues. New degradation data are generated by combining the Stacked Variational Autoencoder (SVAE) and Gated Recurrent Units (GRU) in each time step, which can improve the learning effectiveness of the degradation features. The GRU and the Multi‐layer perceptron calculate the mean and the variance of the degradation distribution for each timestamp, the deeply heterogeneity and temporal feature of the original degraded samples are learned. Then the degradation amount of different samples are predicted. The optimal hyper‐parameters of the SVAE‐GRU are obtained by the grid search method. To verify the effectiveness of the proposed method, three datasets and four methods are used for experiment comparison in this paper. The actual example indicate that the SVAE‐GRU method has the best effect on the degradation generation and prediction. [ABSTRACT FROM AUTHOR]

In recent years, meaningful visual image encryption schemes that the plain image is compressed and encrypted and then hidden into the carrier image have received increasing attention. This paper proposes a new meaningful visual image encryption scheme, which consists of three stages: compression (compression network)—encryption (2D‐SLC hyperchaotic map)—hiding (matrix encoding). First, the advantages of deep learning are explored. It can compress the width, height, channel, and pixel values of the plain image simultaneously. Second, a new 2D‐SLC hyperchaotic map is designed to ensure security. It has a larger chaotic space and better randomness. Finally, to obtain a high‐quality cipher image, the secure secret image is hidden in the grey carrier image by matrix encoding. The scheme can compress and encrypt the grey or colour plain image and then hide it in a grey carrier image. In addition, the theoretical peak signal‐to‐noise ratio (PSNR) between the cipher image and the carrier image is improved from 40.9292 to 42.1785 dB. The total running time is only about 0.35, 0.87 and 3.1 s for a 256 × 256, 512 × 512 and 1024 × 1024 grey or colour plain image, respectively. [ABSTRACT FROM AUTHOR]

With the development of the concept of integrated flight testing, joint testing has become a key research trend. The use of a Logical Range can allow one to overcome the shortcomings of traditional test ranges, allowing for full use of the resources of each range when implementing joint flight testing. However, the Logical Range concept also has problems, such as those relating to the low reusability of test resources and insufficient ability to monitor the resource status in real-time. Considering such problems, a Logical Range framework based on digital twin technology is proposed in this paper. On the basis of this framework, a Logical Range system based on a digital twin for the real-time mapping of real physical behavior is constructed and the three key technologies used in the system are detailed. The feasibility of the framework is successfully verified through a flight test, demonstrating that the proposed framework can provide key support for the application of digital twin technology in the field of flight testing. [ABSTRACT FROM AUTHOR]

Compliance checking is a very important step in engineering construction. With the development of information technology, automated compliance checking (ACC) has been paid more and more attention by researchers. One of the most important steps in automated compliance checking is the representation of the code information. However, the relationship constraint is often ignored in the code information and spatial geometric relationship is challenging to represent. The general code representation method does not have enough ability to identify the situation that does not meet the checking conditions because it is easy to cause semantic ambiguity in the checking results. This paper proposes a code representation method, and the building code information is represented in five parts. Relationships in the engineering domain and spatial relationships can be represented in constraint mode; different spatial relationship constraint-checking methods are also explicated. Constraint subject and constraint item can distinguish checking conditions and requirements, which supports semantic checking results. The mapping between the building information ontology and the code concepts is established, which can be used to automatically generate reasoning rules for compliance checking. Finally, the proposed method is verified by the representation of the China Metro Design Code and the application of the actual Metro model. [ABSTRACT FROM AUTHOR]

This paper proposes a hybrid approach called XTS that uses a combination of techniques to analyze highly imbalanced data with minimum features. XTS combines cost-sensitive XGBoost, a game theory-based model explainer called TreeSHAP, and a newly developed algorithm known as Sequential Forward Evaluation algorithm (SFE). The general aim of XTS is to reduce the number of features required to learn a particular dataset. It assumes that low-dimensional representation of data can improve computational efficiency and model interpretability whilst retaining a strong prediction performance. The efficiency of XTS was tested on a public dataset, and the results showed that by reducing the number of features from 33 to less than five, the proposed model achieved over 99.9% prediction efficiency. XTS was also found to outperform other benchmarked models and existing proof-of-concept solutions in the literature. The dataset contained data related to DNS-over-HTTPS (DoH) tunnels. The top predictors for DoH classification and characterization were identified using interactive SHAP plots, which included destination IP, packet length mode, and source IP. XTS offered a promising approach to improve the efficiency of the detection and analysis of DoH tunnels while maintaining accuracy, which can have important implications for behavioral network intrusion detection systems. [ABSTRACT FROM AUTHOR]

In recent years, various network attacks have emerged. These attacks are often recorded in the form of Pcap data, which contains many attack details and characteristics that cannot be analyzed through traditional methods alone. Therefore, restoring the network attack scenario through scene reconstruction to achieve data regeneration has become an important entry point for detecting and defending against network attacks. However, current network attack scenarios mainly reproduce the attacker's attack steps by building a sequence collection of attack scenarios, constructing an attack behavior diagram, or simply replaying the captured network traffic. These methods still have shortcomings in terms of traffic regeneration. To address this limitation, this paper proposes an SDN-based network attack scenario recovery method. By parsing Pcap data and utilizing network topology reconstruction, probability, and packet sequence models, network traffic data can be regenerated. The experimental results show that the proposed method is closer to the real network, with a higher similarity between the reconstructed and actual attack scenarios. Additionally, this method allows for adjusting the intensity of the network attack and the generated topology nodes, which helps network defenders better understand the attackers' posture and analyze and formulate corresponding security strategies. [ABSTRACT FROM AUTHOR]

Hyperledger Fabric is a distributed ledger solution platform based on a modular architecture. The cryptographic algorithm is the core of the platform to ensure the security and tamper-resistant of the data on the chain. However, the original Fabric platform lacks the protection of user's keys and cryptographic operations. To this end, this paper proposes a data privacy protection method for Hyperledger Fabric based on Trustzone technology, which places the user's key and the cryptographic operation process of private data in the trusted execution environment for protection. The experimental results based on the existing blockchain network show that the scheme can effectively ensure the security of data encryption process and key static storage, greatly reduce the trusted computing base and the attack surface. The performance loss is within an acceptable range. [ABSTRACT FROM AUTHOR]

The object tracking algorithm based on Siamese network often extracts the deep feature of the target to be tracked from the first frame of the video sequence as a template, and uses the template for the whole tracking process. Because the manually annotated target in the first frame of video sequence is more accurate, these algorithms often have stable performance. However, it is difficult to adapt to the changing target features only using the target template extracted from the first frame. Inspired by the feature fusion network based on a transformer, this paper proposes a template update module called multi‐template temporary information fusion module (MTFM), which can be trained offline. By fusing multiple target template features on time series, the template can always adapt to the changes of target appearance in the tracking process. In order to train the MTFM, this paper proposes a training method using time series data and Mean Square Error (MSE) as the loss function. This paper uses the MTFM on SiamFC++ tracker, and obtains good experimental results in three challenging datasets, including VOT2016, OTB100 and GOT‐10k. The running speed of the algorithm on graphics processing unit (GPU) is maintained at about 200fps, which exhibits good real‐time performance. [ABSTRACT FROM AUTHOR]