Graph Neural Networks (GNNs) have achieved impressive performance in semi-supervised graph anomaly detection (GAD). While many GNN variants have been developed for this task, they largely focus on advanced message aggregation schemes, leaving the message routing aspect underexplored. We argue that the commonly used broadcast-based routing can also hinder generalization, particularly in the presence of rare and structurally challenging (vertices with a high-degree) anomalies. To address this, we propose Binary Message Passing (BMP), a novel routing paradigm that models the message flow of each vertex as a binary tree (BMP tree), where vanilla graph convolution is decoupled by its left and right subtrees. Each vertex recursively gathers information from neighbors with higher anomaly probabilities within each subtree, thereby amplifying the propagation of anomaly information across the topology. The anomaly probabilities are estimated and updated by the model itself, enabling adaptive, self-supervised routing over iterations. Furthermore, combining multiple BMP trees into a BMP forest provides multi-scale structural context, enhancing the expressiveness of final vertex embeddings. Extensive experiments show that BMP improves detection performance under limited supervision while exhibiting better generalization across structurally diverse anomalies.

SQL query comprehension is a significant challenge in database and data analysis environments due to complex syntax, diverse join types, and deep nesting. Despite its critical role in backend development and data science, many queries, particularly within legacy systems, often lack adequate comments, which severely hinders code readability, maintainability, and knowledge transfer. Existing approaches to automated SQL comment generation face two main challenges: limited training datasets that inadequately represent real-world analytical queries involving multi-table joins, window functions, and complex aggregations, and an insufficient understanding of SQL-specific logical semantics and schema-related context by Large Language Models (LLMs), even after standard training. Our empirical analysis shows that even after continual pre-training and supervised fine-tuning, LLMs struggle to precisely understand complex SQL semantics, leading to inaccurate or incomplete comments. To address these challenges, we propose SQL-Commenter, an advanced comment generation method based on LLaMA-3.1-8B. First, we construct a comprehensive dataset containing longer, more complex SQL queries with expert-verified, detailed comments. Second, we perform continual pre-training using a large-scale SQL corpus to enhance the LLM’s understanding of SQL syntax and semantics. Then, we conduct supervised fine-tuning with our high-quality dataset. Finally, we introduce Direct Preference Optimization (DPO), which leverages human feedback to significantly improve comment quality. SQL-Commenter utilizes a preference-based loss function that encourages the LLM to increase the probability of preferred outputs while decreasing the probability of non-preferred outputs, thereby enhancing both fine-grained semantic learning, such as distinguishing between different join types, and context-dependent quality assessment based on business logic. We evaluate SQL-Commenter on the authoritative Spider and Bird benchmarks, where it significantly outperforms state-of-the-art baselines. On average, across these datasets, our method surpasses the strongest baseline (Qwen3-14B) by 9.29, 4.99, and 13.23 percentage points on BLEU-4, METEOR, and ROUGE-L, respectively. Moreover, human evaluation demonstrates the superior quality of comments generated by SQL-Commenter in terms of correctness, completeness, and naturalness.

Abstract Distributed Denial of Service attacks (DDoS) are a common and influential network malicious behavior. The timely and accurate detection of Distributed Denial-of-Service (DDoS) attacks constitutes a critically significant research imperative in cyber security. Most current research focuses on classification based on statistical characteristics of network traffic, but less considers the significance of packet payload feature for DDoS attack identification. This paper proposes an adaptive DDoS detection framework integrating machine learning with payload feature engineering. The methodology comprises three phases: 1) constructing a heterogeneous task classification system based on packet metadata analysis, 2) establishing a hierarchical keyword lexicon through payload decomposition and feature pattern mining, followed by feature vector transformation via numerical encoding, and 3) implementing supervised learning algorithms for discriminative model training and feature validity verification. This multilevel feature engineering approach demonstrates enhanced adaptability in DDoS attack pattern recognition compared to conventional detection paradigms. Test results on the public datasets CIC-DDoS-2019, ISCX-SlowDoS-2016 and DoS/DDoS-MQTT-IoT show that the average detection rate of the method in this paper reaches 98.9% for attack behaviors, and the false alarm rate is only 0.1%.

Visual analysis of spatiotemporal density distributions is crucial for understanding spatiotemporal dynamics. However, existing methods suffer from visual occlusion and information loss when simultaneously displaying multiple density distributions. We present Strunkmap as an abstract approach to address these challenges. We introduce anisotropic kernel density estimation to enhance the accuracy of density generation. We extract the trunks of density distributions to identify the overall spatial patterns. Path scanning and trunk-outline matching strategies are employed to preserve local spatial structure. We design a stacked trunk plot that enables lossless density representation while conserving substantial screen space. Based on the visual design, Strunkmap integrates multiple heatmaps within a single map to effectively display temporal evolution of density distributions without visual occlusion. Ablation studies and comparative experiments validate the superiority of Strunkmap in accuracy and efficiency for hotspot identification and trend exploration. Theoretical analysis demonstrates Strunkmap's scalability, which we further verify through large-scale spatiotemporal data visualization. Color encoding schemes and scaling ratios are discussed to illustrate the flexibility. Our evaluations with user feedback demonstrate that Strunkmap is a viable solution with significant potential to real-world applications.

Abstract Code review is a vital but demanding aspect of software development, generating significant interest in automating review comments. Traditional evaluation methods for these comments, primarily based on text similarity, face two major challenges: inconsistent reliability of human-authored comments in open-source projects and the weak correlation of text similarity with objectives like enhancing code quality and detecting defects. This study empirically analyzes benchmark comments using a novel set of criteria informed by prior research and developer interviews. We then similarly revisit the evaluation of existing methodologies. Our evaluation framework, DeepCRCEval, integrates human evaluators and Large Language Models (LLMs) for a comprehensive reassessment of current techniques based on the criteria set. Besides, we also introduce an innovative and efficient baseline, LLM-Reviewer, leveraging the few-shot learning capabilities of LLMs for a target-oriented comparison. Our research highlights the limitations of text similarity metrics, finding that less than 10% of benchmark comments are high quality for automation. In contrast, DeepCRCEval effectively distinguishes between high and low-quality comments, proving to be a more reliable evaluation mechanism. Incorporating LLM evaluators into DeepCRCEval significantly boosts efficiency, reducing time and cost by 88.78% and 90.32%, respectively. Furthermore, LLM-Reviewer demonstrates significant potential of focusing task real targets in comment generation.

The complexity of code reviews has driven efforts to automate review comments, but prior approaches oversimplify this task by treating it as snippet-level code-to-text generation and relying on text similarity metrics like BLEU for evaluation. These methods overlook repository context, real-world merge request evaluation, and defect detection, limiting their practicality. To address these issues, we explore the full automation pipeline within the online recommendation service of a company with nearly 400 million daily active users, analyzing industry-grade C++ codebases comprising hundreds of thousands of lines of code. We identify four key challenges: 1) capturing relevant context, 2) improving key bug inclusion (KBI), 3) reducing false alarm rates (FAR), and 4) integrating human workflows. To tackle these, we propose 1) code slicing algorithms for context extraction, 2) a multi-role LLM framework for KBI, 3) a filtering mechanism for FAR reduction, and 4) a novel prompt design for better human interaction. Our approach, validated on real-world merge requests from historical fault reports, achieves a 2× improvement over standard LLMs and a 10× gain over previous baselines. While the presented results focus on C++, the underlying framework design leverages language-agnostic principles (e.g., AST-based analysis), suggesting potential for broader applicability.

With the increasing security issues in blockchain, smart contract vulnerability detection has become a research focus. Existing vulnerability detection methods have their limitations: 1) Static analysis methods struggle with complex scenarios. 2) Methods based on specialized pre-trained models perform well on specific datasets but have limited generalization capabilities. In contrast, general-purpose Large Language Models (LLMs) demonstrate impressive ability in adapting to new vulnerability patterns. However, they often underperform on specific vulnerability types compared to methods based on specialized pre-trained models. We also observe that explanations generated by generalpurpose LLMs can provide fine-grained code understanding information, contributing to improved detection performance. Inspired by these observations, we propose SAEL, a LLMbased framework for smart contract vulnerability detection. First, we design prompts targeting specific smart contract vulnerabilities to guide general-purpose LLMs in detecting vulnerabilities and providing explanations. The detection results generated by LLMs serve as prediction features. Then, we employ prompt-tuning on CodeT5 and T5 respectively to process contract code and explanations, enhancing model performance on specific tasks. To leverage the strengths of each component, we introduce Adaptive Mixture-of-Experts, a dynamic architecture for smart contract vulnerability detection. This mechanism dynamically adjusts feature weights through a Gating Network, which selects the most relevant features by applying TopK filtering and Softmax normalization, and a Multi-Head Self-Attention mechanism, which enhances cross-feature relationships by processing multiple attention heads in parallel. This design ensures that prediction results for LLMs, explanation features, and contract code features are effectively integrated through gradient optimization. The loss function focuses on the independent prediction performance of each feature and the overall performance of weighted predictions. Experimental results show that SAEL outperforms existing methods in detecting various vulnerabilities.

Rename refactoring is an essential practice in software maintenance, and Variable Rename Refactoring (VRR) is much more challenging than other types of identifiers. Meaningful variable names are critical for code readability and maintainability, as inconsistent variable names can hinder developers from comprehending code. Existing VRR research primarily focuses on Variable Name Consistency Checking (VCC) or variable name recommendation independently, but merely checking inconsistencies or recommending variable names is insufficient: a fully automated process must identify inconsistent names and then rectify them.In this paper, we propose AUVANA, a novel language model based framework to fully AUtomate VAriable reNAme refactoring that automates VRR by integrating inconsistency detection and meaningful variable name generation in Java. Unlike rule-based or semi-automatic approaches, AUVANA eliminates manual effort through two synergistic components: 1) a VCC model that identifies inconsistent variable names and 2) a Variable Name Refactoring (VNR) model that generates consistent replacements. To bridge the gap between pre-training and fine-tuning, we leverage prompt-tuning to improve model performance and tackle the challenge of multiple variable name occurrences. Hard negatives are introduced to address data scarcity.Experimental results demonstrate that AUVANA outperforms SoTA methods. On JavaRef and TL-CodeSum datasets, AUVANA achieves 57.8% and 56.1% Exact Match (EM) accuracy for VNR, exceeding prior baselines by 7.64% and 5.65%, respectively. For VCC, AUVANA attains 95.6% and 94.8% overall accuracy on JavaRef and TL-CodeSum, respectively, showcasing its ability to accurately detect inconsistent variable names. User study demonstrates that AUVANA VRR performance surpasses human in efficiency, precision and EM Accuracy. Artifacts are released to support future research.

The automation of code review activities has emerged as a critical research focus for optimizing development efficiency while ensuring code quality. While recent advancements in Large Language Models (LLMs) have shown promise, existing approaches predominantly isolate the three core code review tasks—review necessity prediction, review comment generation, and code refinement, overlooking their valuable interdependencies. Empirical analysis reveals that isolated-trained comment-generation models often produce superficial comments (e.g., “Undefined ‘userInput’”) due to insufficient understanding of defect patterns, which is what necessity prediction tasks precisely target. Recent efforts to model interdependencies through knowledge distillation remain constrained by static framework designs.To address these challenges, we present MoE-Reviewer, which adopts the Mixture-of-Experts (MoE) framework on the LLaMA model to tackle the interdependence of code review tasks. MoE-Reviewer enables collaborative modeling for the three tasks mentioned above. By integrating dynamic coordination routing strategies and fine-grained expert mechanisms, MoE-Reviewer facilitates effective knowledge sharing across tasks while mitigating parameter interference. Evaluations conducted on the CodeReviewer dataset demonstrated that MoE-Reviewer outperforms existing methods, achieving state-of-the-art performance with an F1-score of 73.2% and improving the BLEU score for review comment generation by 5.32 to 11.62. Additionally, routing analysis further validates the effectiveness of our approach.

Smart contracts are a core component of blockchain ecosystems, but their transparency and immutability make them vulnerable to attacks, leading to significant financial losses. Thus, repairing vulnerabilities in smart contracts is crucial for establishing a trustworthy blockchain environment. Existing smart contract vulnerability repair methods suffer from a critical "one-for-all" design limitation, where a single model is tasked with fixing diverse vulnerability types, leading to suboptimal performance due to insufficient specialization. To address this, we propose MoEFix, a novel framework leveraging a Mixture-of-Experts (MoE) architecture tailored for smart contract characteristics. MoEFix partitions vulnerabilities into subspaces, trains specialized experts for each type (e.g., reentrancy, integer overflow), and employs a vulnerability-aware router to dynamically allocate repairs. We further redesign the repair workflow to align with large language models, enabling end-to-end secure contract generation instead of partial patches, and to achieve this, we curated a dataset of 1,391 contracts covering five critical vulnerability types.To validate our approach, we extend the benchmark PVD test suite. Experiments demonstrate that MoEFix outperforms state-of-the-art methods by 21.64% in overall accuracy, achieving improvements of 26.19% (reentrancy) and 23.08% (delegatecall) for specific vulnerabilities.

Transformers have been widely regarded as a promising direction for breaking through the performance bottlenecks of Graph Neural Networks (GNNs), primarily due to their global receptive fields. However, a recent empirical study suggests that tuned classical GNNs can match or even outperform state-of-the-art Graph Transformers (GTs) on standard node classification benchmarks. Motivated by this fact, we deconstruct several representative GTs to examine how global attention components influence node representations. We find that the global attention module does not provide significant performance gains and may even exacerbate test error oscillations. Consequently, we consider that the Transformer is barely able to learn connectivity patterns that meaningfully complement the original graph topology. Interestingly, we further observe that mitigating such oscillations enables the Transformer to improve generalization in GNNs. In a nutshell, we reinterpret the Transformer through the lens of graph spectrum and reformulate it as a global-aware graph filter with band-pass characteristics and linear complexity. This unique perspective introduces multi-channel filtering constraints that effectively suppress test error oscillations. Extensive experiments (17 homophilous, heterophilous graphs) provide comprehensive empirical evidence for our perspective. This work clarifies the role of Transformers in GNNs and suggests that advancing modern GNN research may still require a return to the graph itself.

Modern code review is essential for software quality, but the complexity of codebases and time demands of manual reviews drive interest in automation for greater efficiency and consistency.However, current automated methods often fail to generate meaningful review comments and lack explainability, limiting developers' understanding and trust.This paper presents EXE-Reviewer, aimed at generating more EXplainable and Effective review comments.To enhance effectiveness, we integrate focus information into an existing model to improve its ability to extract key insights, thereby elevating comment quality.To improve explainability, we connect explanatory information (justification behind solutions) to causality, utilizing causality extraction techniques and introducing an explanatory loss.Furthermore, we devise two metrics to assess the quantity and quality of explanatory content, enhancing insight into the model's explanations.We compare EXE-Reviewer to state-ofthe-art methods in terms of effectiveness and explainability of the generated review comments.Experimental results show that EXE-Reviewer achieves a BLEU-4 score of 7.36%, surpassing the state-of-the-art baseline of 18.52%.Meanwhile, both explainability metrics and empirical study demonstrate notable improvements in explainability of the review comments generated by EXE-Reviewer, highlighting the effectiveness of our approach in generating accurate and comprehensible review comments to developers.

Abstract The multidimensional features of network flows are the main data source for intrusion detection, but excessively low-value features generate accuracy and efficiency challenges. Researchers have used redundant feature reduction to simplify intrusion detections, and feature selection algorithms are beginning to be widely used. This paper presents a novel hybrid feature selection algorithm, CSA-FPA, which combines both a crow search algorithm and a flower pollination algorithm. In this method, properties such as local pollination and the levy flight of FPA are used to balance the global search and local search efficiencies, and parameters such as group distance and probability thresholds are introduced to customize the model’s appearance. The simulation results on the UNSW-NB15 and CIC-IDS2017 datasets show that the proposed CSA-FPA method achieves better detection accuracies than previous algorithms. Using the proposed feature selection method, the AdaBoost classifier achieved a detection accuracy of 99.14% on the CIC-IDS2017 dataset and 97.98% on the UNSW-NB15 dataset.

The industrial internet of things (IIoT) significantly increases industrial productivity but also brings more network security threats.The evolving diversity of cyber attacks has exacerbated security risks in IIoT systems, rendering conventional passive defense mechanisms inadequate against sophisticated intrusions, such as advanced persistent threat(APT), distributed denial of services(DDoS) etc.. This necessitates the adoption of proactive defense strategies, where game theory emerges as a powerful mathematical framework for modeling dynamic attack-defense interactions. Unlike existing surveys that focus solely on game theory fundamentals or IIoT security mechanisms, this paper establishes a novel three-dimensional methodological framework for systematically reviewing game-theoretic applications in IIoT security: (1) theoretical foundations (game components and taxonomy), (2) model implementations (eight principal game types), and (3) comparative analyses (advantages/limitations per model). Crucially, we introduce an innovative classification perspective based on player relationships and payoff computation methods - a significant departure from prior categorizations. We first establish the theoretical framework by examining essential game components and taxonomy classifications. Subsequently, we investigate current research progress through the lens of these eight principal game models, conducting a comprehensive comparative analysis of their category,advantages,drawbacks. The study further identifies three fundamental limitations in existing game-theoretic approaches: imperfect information processing, dynamic adaptation constraints, and multi-agent coordination challenges. Our critical analysis proposed future research directions emphasizing hybrid defense mechanisms, machine learning-enhanced game models, and real-time response architectures. This structured review not only fills the gap in IIoT-specific game-theoretic security surveys but also provides researchers with a unified conceptual framework for developing adaptive security solutions.

Graph Anomaly Detection (GAD) has gained significant attention in areas such as financial risk control and social network security, becoming a critical research problem. Vanilla Graph Neural Networks (GNNs), a popular method for graph modeling, are known to perform poorly in GAD due to the assumption of homophily preferences. This article argues that the issue lies in the insufficient feature extraction ability caused by their single filtering property (low-pass filtering) and revealing the effectiveness of multi-band filtering to deal with GAD. From this, we note two other overlooked issues: (1) How can multi-band band-pass filtering further fuse multi-scale neighborhood information? (2) Adaptation between raw attributes of nodes and graph filters (graph topology). The former bridges the respective advantages of spectral domain and spatial domain, and the latter is an important bottleneck for the encoding capacity of the filters. To address these, we propose a new GAD method, Graph Perturbed Networks (GraphPN). Each hidden layer of GraphPN is a band-pass filter, enabling multi-band and multi-scale filtering through simple stacking and skip connections. We analyze its spectral locality and spatial locality to provide theoretical support. Additionally, GraphPN is supplemented with a tailored feature activation module to complete the adaptation of the above two. This module readjusts node indices and decouples graph convolution, introducing rich topological information to node attributes. In addition to further enhancing detection performance, another possibly counter-intuitive effect is that the distinguishability of the two classes of nodes is improved even before filtering. The proposed method performs well in real-world datasets compared with the current state-of-the-art baselines, which fully demonstrates its superiority. Codes are available at https://github.com/Thankstaro/GraphPN .

Decentralized Finance (DeFi) ecosystem has grown rapidly in the past few years. In the DeFi ecosystem, flash loan is a novel type of uncollateralized loan with nearly negligible lending costs. Malicious attackers can easily borrow a large number of crypto assets, and utilize them to disrupt the price of crypto assets to make a profit. Many flash loan based price manipulation attacks have been reported recently, and caused immense economic losses, e.g., 30 million USD in a single attack. In this paper, we conduct an empirical study on real-world flash loan based attacks in the past two years and present three attack patterns for price manipulation attacks. Then, we propose an approach, LeiShen, to automatically detect price manipulation attacks with asset transfers. We evaluate LeiShen on the first 14,500,000 blocks in Ethereum, and detect 180 attacks with a precision of 78.9%. Among our newly-found attacks, the severest attack has caused a total loss of more than 6.1 million USD.

With the development of blockchain technology, security concerns have become increasingly prominent in recent years. Money laundering through blockchain has been found to generate a significant amount of money and has become a serious threat. Towards money laundering detection in Bitcoin, conventional methods heavily rely on fixed expert rules, leading to low accuracy and poor scalability. Graph convolutional network approaches have improved this issue, but they fail to distinguish the importance of surrounding transactions and the structural information of different transactions. To solve above problems, we propose an approach to detect money laundering on blockchain by mining its transaction records, named AEtransGAT. First, we use a novel approach called transGat as an encoder to determine the significance of surrounding transactions by considering the transaction amount values of transaction flows. The original features and the features after graph embedding are combined to address the issue of feature distortion. Second, we deploy the graph autoencoder as the decoder to learn the overall structural information of different transactions, and the concatenated embedding is used to output the classification results as the detector. Finally, we propose our model based on mutual learning in this task which takes the advantages of both transactions classification loss and structure reconstruction loss. We validate the performance of our model on the Elliptic dataset which is the only large open source dataset in Bitcoin anti-money laundering. The results show that our method outperforms current state-of-the-art methods and is linearly scalable.

With the increasing security issues in the blockchain, smart contract vulnerability detection has gradually become the focus of research. Recently, many approaches have been proposed to detect smart contract vulnerabilities. Despite promising results, these approaches still have three drawbacks: 1) Symbolic execution and static analysis methods are constrained by predefined rules, which limits their adaptability to different vulnerabilities. 2) Most smart contract code contains abundant irrelevant information which is useless for vulnerability detection. 3) Pre-trained models fail to bridge the gap between pre-training and detecting smart contract vulnerabilities.To solve these problems, we propose an approach named PSCVFinder for detecting reentrancy vulnerability and times-tamp dependency vulnerability, which are two severe vulnerabilities in smart contract. To better detect these vulnerabilities, we propose CSCV which is a smart contract slicing method to reduce the irrelevant code. Unlike existing approaches, our model first learns the representation of programming language through the pre-training model, then fully exploits the capacity of large language model with prompt-tuning to precisely detect smart contract vulnerability. We conduct experiments on real-world dataset and the results reflect that PSCVFinder scores 93.83% and 93.49% on two kinds of vulnerabilities in F1-score, surpassing the state-of-the-art baseline by 1.14% and 4.02%, respectively.

Large display interaction has undergone considerable growth, whereas distant pointing poses challenges due to distance limitations and input devices. Smart devices with superior computing power and rich input capabilities aim to surmount these restrictions. However, pointing interactions in single-layer have limited accuracy in large display scenarios. We investigate a hierarchical pointing approach that couples multiple control modes of rotation attitude, touch operation, and pressure simulation with different cursor strategies. Specifically, it covers the dual-layer cursor with the hierarchical structure, the pressure-dependent multistage gain cursor, and the cursor projection technique based on the target acquisition mechanism. We contrast seven distant pointing techniques in two groups of experiments. Our results indicate that the hierarchical interaction strategy improves user performance, and cursor projection achieves an optimal trade-off between velocity and accuracy for high Fitts’ index of difficulty (ID) contexts.

The randomness and variability of IP addresses challenge the identity uniqueness of internet hosts. Accurately identifying internet hosts on the premise of protecting users’ privacy is difficult. In this paper, we demonstrate that the network behaviour characteristics of internet hosts often have self-similar characteristics, and propose a new method for host identification based on network activity self-similarity (NASS). In this method, the multidimensional behaviour features of internet hosts are collected from network traffic, and the time series of behaviour features are constructed. Then, after noise reduction, Mahalanobis distance is applied to measure the distance between the time series of different time windows of any two hosts. The distance measurement results are ranked, and host identification is realized according to the ranking. NASS can accurately identify the network host without violating user privacy and is suitable for encrypted communication environments. The experimental results show that the accuracy of NASS is 83.67%.

Bitcoin has emerged as a popular decentralized cryptocurrency and attracted much attention from the public. Bitcoin embodies the Nakamoto consensus to reach an agreement about its blockchain ledger. However, the Nakamoto consensus can suffer from selfish mining attacks. Existing studies on selfish mining usually assume that the total mining power is divided into two parts (i.e., honest and selfish), and ignore propagation delay among miners. The assumptions cannot reflect real-world scenarios, in which multiple miners generate blocks at a fixed interval and propagate them with certain delay. Therefore, it is unknown how the practical factors, i.e., multiple miners and propagation delay, can affect selfish mining.In this paper, we explore the impact of multiple miners and propagation delay on selfish mining. First, we propose a new selfish mining strategy that can handle these factors. Second, we design a simulation approach to analyze the performance of the new selfish mining strategy. From our empirical study we observe many interesting findings that can be utilized in combating selfish mining. For example, the blockchain system with a higher orphan rate is more vulnerable to the selfish mining attack.

The blockchain technology is regarded as a significant trust-building technology and has attracted much attention from the public. The longest chain rule has been widely applied in blockchain systems to reach consensus on the distributed ledger. However, the longest chain rule cannot support a higher transaction throughput due to its lower security. As an alternative solution to the longest chain rule, GHOST is proposed as a safer consensus rule. Existing studies show that the longest chain rule can suffer from selfish mining attacks. However, it is unclear how selfish mining attacks perform on GHOST. In this paper, we explore the performance of selfish mining on GHOST. We first propose the original selfish mining (GHOST-SM) and stubborn mining (GHOST-StuM) for GHOST. We then evaluate these two selfish mining strategies on our blockchain simulation system. The experimental result shows that GHOST achieves better security than the longest chain rule. However, when the block generation rate increases, the security of GHOST is close to the longest chain rule. For example, the threshold for selfish mining attacks of GHOST is increased by 47.55% and 0.60% compared to the longest chain rule corresponding to the block generation interval of 1 second and 15 seconds.

3D facial landmark, which offers more expressive and occlusive information than its 2D counterpart, receives more and more attention from researchers in recent years. The top performing algorithms for 3D facial landmark detection are mainly divided into two categories: the two-step approach and the volume representation method. However, the former lacks the relation of depth with plat and the latter leads to large computation. In this paper, we propose the Combined Heatmap and Coordinate Regression (CHCR), which is an end-to-end method for 3D facial landmark detection from a single 2D image. To achieve that, we innovatively present the combined heatmap of three channels, and each channel of heatmap records the likelihoods of landmarks location of any two different axes. Such representation maintains the relation of various view while decreases either the channels for encoding or dimension for decoding. Then we retrieve the 3D coordinate vectors from corresponding combined heatmap by coordinate regression. Hence, an encoder-decoder network with a simple CNN attached to an hourglass module is designed to cope with the whole process. Experiments show our model is extremely light-weighted and runs faster than any other methods while on high performance of accuracy.

The class imbalance problem exists in many real-world applications such as fraud detection, medical diagnosis and spam filtering, and seriously influences the performance of learning algorithms. Randomly undersampling is a famous method to solve the problem. However, it cannot well extract the samples nearby the cross-edge of majority and minority classes due to its randomness, while these samples are very important for a classifier since they influence the classification performance. In this paper, we propose a novel Gaussian Mixture Undersampling (GMUS for short). GMUS mainly contains three steps. Firstly, a Gaussian Mixture Model (GMM) is applied to fit the majority samples. Secondly, considering the probability density function (PDF) of predicted minority samples on the well-fitted GMM, the maximum of PDF is selected as the cross-edge of two classes. Finally, we undersample the majority samples near the cross-edge. We do experiments on 16 public datasets and the results demonstrate that GMUS can sample more informative instances and thus improve the performance of classifiers compared with the state-of-the-art undersampling methods. We also apply GMUS to the credit card fraud detection and obtain a good performance.

We propose a real-time 3D model-based method that continuously recognizes dimensional emotions from facial expressions in natural communications. In our method, 3D facial models are restored from 2D images, which provide crucial clues for the enhancement of robustness to overcome large changes including out-of-plane head rotations, fast head motions and partial facial occlusions. To accurately recognize the emotion, a novel random forest-based algorithm which simultaneously integrates two regressions for 3D facial tracking and continuous emotion estimation is constructed. Moreover, via the reconstructed 3D facial model, temporal information and user-independent emotion presentations are also taken into account through our image fusion process. The experimental results show that our algorithm can achieve state-of-the-art result with higher Pearson's correlation coefficient of continuous emotion recognition in real time.

In multi-touch interactive systems, it is of great significance to distinguish which hand of the user is touching the surface in real time. Left-right hand distinction is essential for recognizing the multi-finger gestures and further fully exploring the potential of bimanual interaction. However, left-right hand distinction is beyond the capability of most existing multi-touch systems. In this paper, we present a new method for left and right hand distinction based on the human anatomy, work area, finger orientation and finger position. Considering the ergonomics principles of gesture designing, the body-forearm triangle model was proposed. Furthermore, a heuristic algorithm was introduced to group multi-touch contact points and then made left-right hand distinction. A dataset of 2880 images has been set up to evaluate the proposed left-right hand distinction method. The experimental results demonstrate that our method can guarantee the high recognition accuracy and real time performance in freely bimanual multi-touch interactions.

Smoothed particle hydrodynamics (SPH) is efficient, mass preserving, and flexible in handling topological changes. However, sparsely sampled thin features are difficult to simulate in SPH-based free surface flows, due to a number of robustness and stability issues. In this article, we address this problem from two perspectives: the robustness of surface forces and the numerical instability of thin features. We present a new surface tension force scheme based on a free surface energy functional, under the diffuse interface model. We develop an efficient way to calculate the air pressure force for free surface flows, without using air particles. Compared with previous surface force formulae, our formulae are more robust against particle sparsity in thin feature cases. To avoid numerical instability on thin features, we propose to adjust the internal pressure force by estimating the internal pressure at two scales and filtering the force using a geometry-aware anisotropic kernel. Our result demonstrates the effectiveness of our algorithms in handling a variety of sparsely sampled thin liquid features, including thin sheets, thin jets, and water splashes.

Sparse bundle adjustment is widely used in many computer vision applications. In this paper, we propose a method for performing bundle adjustments using the L1norm. After linearizing the mapping function in bundle adjustment on its first order, the kernel step is to compute the L1norm equations. Considering the sparsity of the Jacobian matrix in linearizing, we find two practical methods to solve the L1norm equations. The first one is an interior-point method, which transfer the original problem to a problem of solving a sequence of L2norm equations, and the second one is a decomposition method which uses the differentiability of linear programs and represents the optimal updating of parameters of 3D points by the updating variables of camera parameters. The experiments show that the method performs better for both synthetically generated and real data sets in the presence of outliers or Laplacian noise compared with the L2norm bundle adjustment, and the method is efficient among the state of the art L1minimization methods.

Simulating solid-fluid coupling with the classical meshless methods is an difficult issue due to the lack of the Kronecker delta property of the shape functions when enforcing the essential boundary conditions. In this work, we present a novel staggered meshless method to overcome this problem. We create a set of staggered particles from the original particles in each time step by mapping the mass and momentum onto these staggered particles, aiming to stagger the velocity field from the pressure field. Based on this arrangement, an new approximate projection method is proposed to enforce divergence-free on the fluid velocity with compatible boundary conditions. In the simulations, the method handles the fluid and solid in a unified meshless manner and generalizes the formulations for computing the viscous and pressure forces. To enhance the robustness of the algorithm, we further propose a new framework to handle the degeneration case in the solid-fluid coupling, which guarantees stability of the simulation. The proposed method offers the benefit that various slip boundary conditions can be easily implemented. Besides, explicit collision handling for the fluid and solid is avoided. The method is easy to implement and can be extended from the standard SPH algorithm in a straightforward manner. The paper also illustrates both one-way and two-way couplings of the fluids and rigid bodies using several test cases in two and three dimensions.

The classical Mean Shift can't change the scale of tracking window in real time while tracking target is changing in size. This paper adopts graph cuts theory to the problem of scale adaptation for Mean Shift tracking. According to the result of Mean Shift iteration in every frame, implementing graph cuts using skin color Gaussian mixture model(GMM) in a small area around it, and updating tracking window size through the largest skin lump among the result of graph cuts. Experimental results clearly demonstrate that the method can reflect the real scale change of tracking target, avoid the interference of other objects in background, and has good usability and robustness. Besides it enriches manipulation method of Human Computer Interaction by controlling entertainment games.

Research on complex shape recognition showed that the shape context algorithm is sensitive to relative position variation of articulation. Aimed at this problem, a shape recognition method is proposed based on local shape filling rate of various object silhouettes. We take each landmark point as a circle center and use as its radius. Then, under a particular radius, the ratio between the covered silhouette pixels and the total pixels is defined as local shape filling rate. Thus, different radius may form different local shape filling rates. All landmark points with different radius will constitute a characteristic matrix which can effectively reflects the entire statistical property of the object shape. Experiments on a variety of shape databases show that the novel method is insensitive to articulation and less influenced by the number of landmark points, so our algorithm has strong power in describing object details.

Co-CreativePen toolkit is a pen-based 3D toolkit for children cooperatively designing virtual environment. This toolkit is used to construct different applications involved with distributed pen-based 3D interaction. In this toolkit, sketch method is encapsulated as kinds of interaction techniques. Children can use pen to construct 3D and IBR objects, to navigate in the virtual world, to select and manipulate virtual objects, and to communicate with other children. Children can use pen to select other children in the virtual world, and use pen to write message to children selected. The distributed architecture of Co-CreativePen toolkit is based on the CORBA. A common scene graph is managed in the server with several copies of this graph are managed in every client. Every changes of the scene graph in client will cause the change in the server and other client