Data race is one of the most important concurrent anomalies in multi-threaded *** con-straint-based techniques are leveraged into race detection,which is able to find all the races that can be found by any oth-er soun...
详细信息
Data race is one of the most important concurrent anomalies in multi-threaded *** con-straint-based techniques are leveraged into race detection,which is able to find all the races that can be found by any oth-er sound race ***,this constraint-based approach has serious limitations on helping programmers analyze and understand data ***,it may report a large number of false positives due to the unrecognized dataflow propa-gation of the ***,it recommends a wide range of thread context switches to schedule the reported race(in-cluding the false one)whenever this race is exposed during the constraint-solving *** ad hoc recommendation imposes too many context switches,which complicates the data race *** address these two limitations in the state-of-the-art constraint-based race detection,this paper proposes DFTracker,an improved constraint-based race detec-tor to recommend each data race with minimal thread context ***,we reduce the false positives by ana-lyzing and tracking the dataflow in the *** this means,DFTracker thus reduces the unnecessary analysis of false race *** further propose a novel algorithm to recommend an effective race schedule with minimal thread con-text switches for each data *** experimental results on the real applications demonstrate that 1)without removing any true data race,DFTracker effectively prunes false positives by 68%in comparison with the state-of-the-art constraint-based race detector;2)DFTracker recommends as low as 2.6-8.3(4.7 on average)thread context switches per data race in the real world,which is 81.6%fewer context switches per data race than the state-of-the-art constraint based race ***,DFTracker can be used as an effective tool to understand the data race for programmers.
Adversarial examples(AEs) are an additive amalgamation of clean examples and artificially malicious perturbations. Attackers often leverage random noise and multiple random restarts to initialize perturbation starting...
详细信息
Adversarial examples(AEs) are an additive amalgamation of clean examples and artificially malicious perturbations. Attackers often leverage random noise and multiple random restarts to initialize perturbation starting points, thereby increasing the diversity of AEs. Given the non-convex nature of the loss function, employing randomness to augment the attack's success rate may lead to considerable computational overhead. To overcome this challenge,we introduce the one-hot mean square error loss to guide the initialization. This loss is combined with the strongest first-order attack, the projected gradient descent, alongside a dynamic attack step size adjustment strategy to form a comprehensive attack process. Through experimental validation, we demonstrate that our method outperforms baseline attacks in constrained attack budget scenarios and regular experimental settings. This establishes it as a reliable measure for assessing the robustness of deep learning models. We explore the broader application of this initialization strategy in enhancing the defense impact of few-shot classification models. We aspire to provide valuable insights for the community in designing attack and defense mechanisms.
Skill learning through reinforcement learning has significantly progressed in recent years. However, it often struggles to efficiently find optimal or near-optimal policies due to the inherent trial-and-error explorat...
详细信息
Skill learning through reinforcement learning has significantly progressed in recent years. However, it often struggles to efficiently find optimal or near-optimal policies due to the inherent trial-and-error exploration in reinforcement learning. Although algorithms have been proposed to enhance skill learning efficacy, there is still much room for improvement in terms of skill learning performance and training stability. In this paper, we propose an algorithm called skill enhancement learning with knowledge distillation(SELKD), which integrates multiple actors and multiple critics for skill learning. SELKD employs knowledge distillation to establish a mutual learning mechanism among actors. To mitigate critic overestimation bias,we introduce a novel target value calculation method. We also perform theoretical analysis to ensure the convergence of SELKD. Finally, experiments are conducted on several continuous control tasks, illustrating the effectiveness of the proposed algorithm.
Communication is crucial to the performance of distributed training. Today's solutions tightly couple the control and data planes and lack flexibility, generality, and performance. In this study, we present SDCC, ...
详细信息
Communication is crucial to the performance of distributed training. Today's solutions tightly couple the control and data planes and lack flexibility, generality, and performance. In this study, we present SDCC, a software-defined collective communication framework for distributed training. SDCC is based on the principle of modern systems design to effectively decouple the control plane from the data *** abstracts the operations for collective communication in distributed training with dataflow operations and unifies computing and communication with a single dataflow graph. The abstraction, together with the unification, is powerful: it enables users to easily express new and existing collective communication algorithms and optimizations, simplifies the integration with different computing engines(e.g., Py Torch and Tensor Flow) and network transports(e.g., Linux TCP and kernel bypass), and allows the system to improve performance by exploiting parallelism exposed by the dataflow graph. We further demonstrate the benefits of SDCC in four use cases.
Stock price prediction is a typical complex time series prediction problem characterized by dynamics,nonlinearity,and *** paper introduces a generative adversarial network model that incorporates an attention mechanis...
详细信息
Stock price prediction is a typical complex time series prediction problem characterized by dynamics,nonlinearity,and *** paper introduces a generative adversarial network model that incorporates an attention mechanism(GAN-LSTM-Attention)to improve the accuracy of stock price ***,the generator of this model combines the Long and Short-Term Memory Network(LSTM),the Attention Mechanism and,the Fully-Connected Layer,focusing on generating the predicted stock *** discriminator combines the Convolutional Neural Network(CNN)and the Fully-Connected Layer to discriminate between real stock prices and generated stock ***,to evaluate the practical application ability and generalization ability of the GAN-LSTM-Attention model,four representative stocks in the United States of America(USA)stock market,namely,Standard&Poor’s 500 Index stock,Apple Incorporatedstock,AdvancedMicroDevices Incorporatedstock,and Google Incorporated stock were selected for prediction experiments,and the prediction performance was comprehensively evaluated by using the three evaluation metrics,namely,mean absolute error(MAE),root mean square error(RMSE),and coefficient of determination(R2).Finally,the specific effects of the attention mechanism,convolutional layer,and fully-connected layer on the prediction performance of the model are systematically analyzed through ablation *** results of experiment show that the GAN-LSTM-Attention model exhibits excellent performance and robustness in stock price prediction.
With the rapid proliferation of Internet ofThings(IoT)devices,ensuring their communication security has become increasingly *** and smart contract technologies,with their decentralized nature,provide strong security g...
详细信息
With the rapid proliferation of Internet ofThings(IoT)devices,ensuring their communication security has become increasingly *** and smart contract technologies,with their decentralized nature,provide strong security guarantees for ***,at the same time,smart contracts themselves face numerous security challenges,among which reentrancy vulnerabilities are particularly *** detection tools for reentrancy vulnerabilities often suffer from high false positive and false negative rates due to their reliance on identifying patterns related to specific transfer *** address these limitations,this paper proposes a novel detection method that combines pattern matching with deep ***,we carefully identify and define three common patterns of reentrancy vulnerabilities in smart ***,we extract key vulnerability features based on these ***,we employ a Graph Attention Neural Network to extract graph embedding features from the contract graph,capturing the complex relationships between different components of the ***,we use an attention mechanism to fuse these two sets of feature information,enhancing the weights of effective information and suppressing irrelevant information,thereby significantly improving the accuracy and robustness of vulnerability *** results demonstrate that our proposed method outperforms existing state-ofthe-art techniques,achieving a 3.88%improvement in accuracy compared to the latest vulnerability detection model AME(Attentive Multi-Encoder Network).This indicates that our method effectively reduces false positives and false negatives,significantly enhancing the security and reliability of smart contracts in the evolving IoT ecosystem.
In low-light image enhancement,prevailing Retinex-based methods often struggle with precise illumina-tion estimation and brightness *** can result in issues such as halo artifacts,blurred edges,and diminished details ...
详细信息
In low-light image enhancement,prevailing Retinex-based methods often struggle with precise illumina-tion estimation and brightness *** can result in issues such as halo artifacts,blurred edges,and diminished details in bright regions,particularly under non-uniform illumination *** propose an innovative approach that refines low-light images by leveraging an in-depth awareness of local content within the *** introducing multi-scale effective guided filtering,our method surpasses the limitations of traditional isotropic filters,such as Gaussian filters,in handling non-uniform *** dynamically adjusts regularization parameters in response to local image characteristics and significantly integrates edge perception across different *** balanced approach achieves a harmonious blend of smoothing and detail preservation,enabling more accurate illumination ***,we have designed an adaptive gamma correction function that dynamically adjusts the brightness value based on local pixel intensity,further balancing enhancement effects across different brightness levels in the *** results demonstrate the effectiveness of our proposed method for non-uniform illumination images across various *** exhibits superior quality and objective evaluation scores compared to existing *** method effectively addresses potential issues that existing methods encounter when processing non-uniform illumination images,producing enhanced images with precise details and natural,vivid colors.
This study introduces a multifunctional device based on Cu_(2)O/g-C_(3)N_(4) monitoring and purification p–n heterojunctions(MPHs),seamlessly integrating surface-enhanced Raman scattering(SERS)detection with photocat...
详细信息
This study introduces a multifunctional device based on Cu_(2)O/g-C_(3)N_(4) monitoring and purification p–n heterojunctions(MPHs),seamlessly integrating surface-enhanced Raman scattering(SERS)detection with photocatalytic degradation *** SERS and photocatalytic performances of the Cu_(2)O in various morphologies,g-C_(3)N_(4) nanosheets(NSs)and Cu_(2)O/g-C_(3)N_(4) MPHs with different g-C_(3)N_(4) mass ratios were systematically evaluated,with a particular emphasis on the Cu_(2)O/g-C_(3)N_(4)-0.2 MPH,where g-C_(3)N_(4) constituted 20%of the total *** optical and electrochemical tests revealed that the Cu_(2)O/g-C_(3)N_(4)-0.2 MPH effectively enhances charge separation and reduces charge transfer *** Cu_(2)O/g-C_(3)N_(4)-0.2 SERS sensor exhibited a relative standard deviation(RSD)below 15%and achieved an enhancement factor(EF)of 2.43×106 for 4-ATP detection,demonstrating its high sensitivity and ***,it demonstrated a 98.3%degradation efficiency for methyl orange(MO)under visible light within 90 ***,even after 216 days,its photocatalytic efficiency remained at 93.7%,and it retained an 84.0%efficiency after four *** and SEM analyses before and after cycling,as well as after 216 days,confirmed the structural and morphological stability of the composite,demonstrating its cyclic and long-term *** excellent performance of the Cu_(2)O/g-C_(3)N_(4) MPH is attributed to its Z-type mechanism,as verified by radical trapping *** evaluation of the self-cleaning performance of the Cu_(2)O/g-C_(3)N_(4)-0.2 SERS sensor demonstrated that its Z-scheme structure not only provides excellent self-cleaning capability but also enables the detection of both individual and mixed pollutants,while significantly enhancing the SERS signal response through an effective charge transfer enhancement mechanism.
Graph similarity learning aims to calculate the similarity between pairs of *** unsupervised graph similarity learning methods based on contrastive learning encounter challenges related to random graph augmentation st...
详细信息
Graph similarity learning aims to calculate the similarity between pairs of *** unsupervised graph similarity learning methods based on contrastive learning encounter challenges related to random graph augmentation strategies,which can harm the semantic and structural information of graphs and overlook the rich structural information present in *** address these issues,we propose a graph similarity learning model based on learnable augmentation and multi-level contrastive ***,to tackle the problem of random augmentation disrupting the semantics and structure of the graph,we design a learnable augmentation method to selectively choose nodes and edges within the *** enhance contrastive levels,we employ a biased random walk method to generate corresponding subgraphs,enriching the contrastive ***,to solve the issue of previous work not considering multi-level contrastive learning,we utilize graph convolutional networks to learn node representations of augmented views and the original graph and calculate the interaction information between the attribute-augmented and structure-augmented views and the original *** goal is to maximize node consistency between different views and learn node matching between different graphs,resulting in node-level representations for each *** representations are then obtained through pooling operations,and we conduct contrastive learning utilizing both node and subgraph ***,the graph similarity score is computed according to different downstream *** conducted three sets of experiments across eight datasets,and the results demonstrate that the proposed model effectively mitigates the issues of random augmentation damaging the original graph’s semantics and structure,as well as the insufficiency of contrastive ***,the model achieves the best overall performance.
CoSb3, as a medium temperature semiconductor thermoelectric material, has attracted much attention due to the abundant adjustable space provided by the Sb12 icosahedral cage structure and its excellent carrier mobilit...
详细信息
暂无评论