Federated Graph Neural Networks (FedGNNs) have achieved significant success in representation learning for graph data, enabling collaborative training among multiple parties without sharing their raw graph data and so...
详细信息
Federated Graph Neural Networks (FedGNNs) have achieved significant success in representation learning for graph data, enabling collaborative training among multiple parties without sharing their raw graph data and solving the data isolation problem faced by centralized GNNs in data-sensitive scenarios. Despite the plethora of prior work on inference attacks against centralized GNNs, the vulnerability of FedGNNs to inference attacks has not yet been widely explored. It is still unclear whether the privacy leakage risks of centralized GNNs will also be introduced in FedGNNs. To bridge this gap, we present PIAFGNN, the first property inference attack (PIA) against FedGNNs. Compared with prior works on centralized GNNs, in PIAFGNN, the attacker can only obtain the global embedding gradient distributed by the central server. The attacker converts the task of stealing the target user’s local embeddings into a regression problem, using a regression model to generate the target graph node embeddings. By training shadow models and property classifiers, the attacker can infer the basic property information within the target graph that is of interest. Experiments on three benchmark graph datasets demonstrate that PIAFGNN achieves attack accuracy of over 70% in most cases, even approaching the attack accuracy of inference attacks against centralized GNNs in some instances, which is much higher than the attack accuracy of the random guessing method. Furthermore, we observe that common defense mechanisms cannot mitigate our attack without affecting the model’s performance on mainly classification tasks.
Coronavirus disease 2019(Covid-19)is a life-threatening infectious disease caused by a newly discovered strain of the *** by the end of 2020,Covid-19 is still not fully understood,but like other similar viruses,the ma...
详细信息
Coronavirus disease 2019(Covid-19)is a life-threatening infectious disease caused by a newly discovered strain of the *** by the end of 2020,Covid-19 is still not fully understood,but like other similar viruses,the main mode of transmission or spread is believed to be through droplets from coughs and sneezes of infected *** accurate detection of Covid-19 cases poses some questions to scientists and *** two main kinds of tests available for Covid-19 are viral tests,which tells you whether you are currently infected and antibody test,which tells if you had been infected ***-tine Covid-19 test can take up to 2 days to complete;in reducing chances of false negative results,serial testing is *** image processing by means of using Chest X-ray images and Computed Tomography(CT)can help radiologists detect the *** imaging approach can detect certain characteristic changes in the lung associated with *** this paper,a deep learning model or tech-nique based on the Convolutional Neural Network is proposed to improve the accuracy and precisely detect Covid-19 from Chest Xray scans by identifying structural abnormalities in scans or X-ray *** entire model proposed is categorized into three stages:dataset,data pre-processing andfinal stage being training and classification.
FDTD method is a common approach for electromagnetic propagation, scattering and coupling simulation. Conventional FDTD with universal mesh requires numerous computations to represent solve problems with multi-scale s...
详细信息
Community detection is a fundamental task in complex network analysis, aiming to partition networks into tightly multiple dense subgraphs. While community detection has been widely studied, existing methods often lack...
详细信息
Community detection is a fundamental task in complex network analysis, aiming to partition networks into tightly multiple dense subgraphs. While community detection has been widely studied, existing methods often lack interpretability, making it challenging to explain key aspects such as node assignments, community boundaries, and inter-community relationships. In this paper, the explainable community detection issue is addressed, in which each community is characterized using a central node and its corresponding radius. The central node represents the most representative node in the community, while the radius defines its influence scope. Such an explainable community detection issue is formulated as an optimization problem in which the objective is to maximize central node's coverage and accuracy in explaining its associated community. To solve this problem, two algorithms are developed: a naive algorithm and a fast approximate algorithm that incorporate heuristic strategies to improve computational efficiency. Experimental results on 9 real-world networks demonstrate that the proposed methods can effectively interpret community structures with high accuracy and efficiency. More precisely, the objective function values achieved by the identified pairs of center and radius exceed 0.7 on most communities and the running time is generally no more than 10 s on a network with approximatively one thousand nodes. The source code of the proposed methods can be found at: https://***/xuannnn523/CCTS.
A new meaningful image encryption algorithm based on compressive sensing(CS)and integer wavelet transformation(IWT)is proposed in this *** of all,the initial values of chaotic system are encrypted by RSA algorithm,and...
详细信息
A new meaningful image encryption algorithm based on compressive sensing(CS)and integer wavelet transformation(IWT)is proposed in this *** of all,the initial values of chaotic system are encrypted by RSA algorithm,and then they are open as public *** make the chaotic sequence more random,a mathematical model is constructed to improve the random ***,the plain image is compressed and encrypted to obtain the secret ***,the secret image is inserted with numbers zero to extend its size same to the plain *** applying IWT to the carrier image and discrete wavelet transformation(DWT)to the inserted image,the secret image is embedded into the carrier ***,a meaningful carrier image embedded with secret plain image can be obtained by inverse ***,the measurement matrix is built by both chaotic system and Hadamard matrix,which not only retains the characteristics of Hadamard matrix,but also has the property of control and synchronization of chaotic ***,information entropy of the plain image is employed to produce the initial conditions of chaotic *** a result,the proposed algorithm can resist known-plaintext attack(KPA)and chosen-plaintext attack(CPA).By the help of asymmetric cipher algorithm RSA,no extra transmission is needed in the *** simulations show that the normalized correlation(NC)values between the host image and the cipher image are *** is to say,the proposed encryption algorithm is imperceptible and has good hiding effect.
With the increasing pervasiveness of mobile devices such as smartphones,smart TVs,and wearables,smart sensing,transforming the physical world into digital information based on various sensing medias,has drawn research...
详细信息
With the increasing pervasiveness of mobile devices such as smartphones,smart TVs,and wearables,smart sensing,transforming the physical world into digital information based on various sensing medias,has drawn researchers’great *** different sensing medias,WiFi and acoustic signals stand out due to their ubiquity and zero hardware *** on different basic principles,researchers have proposed different technologies for sensing applications with WiFi and acoustic signals covering human activity recognition,motion tracking,indoor localization,health monitoring,and the *** enable readers to get a comprehensive understanding of ubiquitous wireless sensing,we conduct a survey of existing work to introduce their underlying principles,proposed technologies,and practical *** we also discuss some open issues of this research *** survey reals that as a promising research direction,WiFi and acoustic sensing technologies can bring about fancy applications,but still have limitations in hardware restriction,robustness,and applicability.
High-order discretizations of partial differential equations(PDEs)necessitate high-order time integration schemes capable of handling both stiff and nonstiff operators in an efficient ***-explicit(IMEX)integration bas...
详细信息
High-order discretizations of partial differential equations(PDEs)necessitate high-order time integration schemes capable of handling both stiff and nonstiff operators in an efficient ***-explicit(IMEX)integration based on general linear methods(GLMs)offers an attractive solution due to their high stage and method order,as well as excellent stability *** IMEX characteristic allows stiff terms to be treated implicitly and nonstiff terms to be efficiently integrated *** work develops two systematic approaches for the development of IMEX GLMs of arbitrary order with stages that can be solved in *** first approach is based on diagonally implicit multi-stage integration methods(DIMSIMs)of types 3 and *** second is a parallel generalization of IMEX Euler and has the interesting feature that the linear stability is independent of the order of *** experiments confirm the theoretical rates of convergence and reveal that the new schemes are more efficient than serial IMEX GLMs and IMEX Runge-Kutta methods.
Transformer-based models like large language models (LLMs) have attracted significant attention in recent years due to their superior performance. A long sequence of input tokens is essential for industrial LLMs to pr...
详细信息
Transformer-based models like large language models (LLMs) have attracted significant attention in recent years due to their superior performance. A long sequence of input tokens is essential for industrial LLMs to provide better user services. However, memory consumption increases quadratically with the increase of sequence length, posing challenges for scaling up long-sequence training. Current parallelism methods produce duplicated tensors during execution, leaving space for improving memory efficiency. Additionally, tensor parallelism (TP) cannot achieve effective overlap between computation and communication. To solve these weaknesses, we propose a general parallelism method called memory-efficient tensor parallelism (METP), designed for the computation of two consecutive matrix multiplications and a possible function between them (O = f(AB)C), which is the kernel computation component in Transformer training. METP distributes subtasks of computing O to multiple devices and uses send/recv instead of collective communication to exchange submatrices for finishing the computation, avoiding producing duplicated tensors. We also apply the double buffering technique to achieve better overlap between computation and communication. We present the theoretical condition of full overlap to help instruct the long-sequence training of Transformers. Suppose the parallel degree is p;through theoretical analysis, we prove that METP provides O(1/p(3)) memory overhead when not using FlashAttention to compute attention and could save at least 41.7% memory compared to TP when using FlashAttention to compute multi-head self-attention. Our experimental results demonstrate that METP can increase the sequence length by 2.38-2.99 times compared to other methods when using eight A100 graphics processing units (GPUs).
Industrial Internet of Things(IIoT)systems depend on a growing number of edge devices such as sensors,controllers,and robots for data collection,transmission,storage,and *** kind of malicious or abnormal function by e...
详细信息
Industrial Internet of Things(IIoT)systems depend on a growing number of edge devices such as sensors,controllers,and robots for data collection,transmission,storage,and *** kind of malicious or abnormal function by each of these devices can jeopardize the security of the entire ***,they can allow malicious software installed on end nodes to penetrate the *** paper presents a parallel ensemble model for threat hunting based on anomalies in the behavior of IIoT edge *** proposed model is flexible enough to use several state-of-the-art classifiers as the basic learner and efficiently classifies multi-class anomalies using the Multi-class AdaBoost and majority *** evaluations using a dataset consisting of multi-source normal records and multi-class anomalies demonstrate that our model outperforms existing approaches in terms of accuracy,F1 score,recall,and precision.
In this paper,an Observation Points Classifier Ensemble(OPCE)algorithm is proposed to deal with High-Dimensional Imbalanced Classification(HDIC)problems based on data processed using the Multi-Dimensional Scaling(MDS)...
详细信息
In this paper,an Observation Points Classifier Ensemble(OPCE)algorithm is proposed to deal with High-Dimensional Imbalanced Classification(HDIC)problems based on data processed using the Multi-Dimensional Scaling(MDS)feature extraction ***,dimensionality of the original imbalanced data is reduced using MDS so that distances between any two different samples are preserved as well as ***,a novel OPCE algorithm is applied to classify imbalanced samples by placing optimised observation points in a low-dimensional data ***,optimization of the observation point mappings is carried out to obtain a reliable assessment of the unknown *** experiments have been conducted to evaluate the feasibility,rationality,and effectiveness of the proposed OPCE algorithm using seven benchmark HDIC data *** results show that(1)the OPCE algorithm can be trained faster on low-dimensional imbalanced data than on high-dimensional data;(2)the OPCE algorithm can correctly identify samples as the number of optimised observation points is increased;and(3)statistical analysis reveals that OPCE yields better HDIC performances on the selected data sets in comparison with eight other HDIC *** demonstrates that OPCE is a viable algorithm to deal with HDIC problems.
暂无评论