Transformer-based models have significantly advanced binary code similarity detection(BCSD)by leveraging their semantic encoding capabilities for efficient function matching across diverse compilation settings.Althoug...Transformer-based models have significantly advanced binary code similarity detection(BCSD)by leveraging their semantic encoding capabilities for efficient function matching across diverse compilation settings.Although adversarial examples can strategically undermine the accuracy of BCSD models and protect critical code,existing techniques predominantly depend on inserting artificial instructions,which incur high computational costs and offer limited diversity of perturbations.To address these limitations,we propose AIMA,a novel gradient-guided assembly instruction relocation method.Our method decouples the detection model into tokenization,embedding,and encoding layers to enable efficient gradient computation.Since token IDs of instructions are discrete and nondifferentiable,we compute gradients in the continuous embedding space to evaluate the influence of each token.The most critical tokens are identified by calculating the L2 norm of their embedding gradients.We then establish a mapping between instructions and their corresponding tokens to aggregate token-level importance into instructionlevel significance.To maximize adversarial impact,a sliding window algorithm selects the most influential contiguous segments for relocation,ensuring optimal perturbation with minimal length.This approach efficiently locates critical code regions without expensive search operations.The selected segments are relocated outside their original function boundaries via a jump mechanism,which preserves runtime control flow and functionality while introducing“deletion”effects in the static instruction sequence.Extensive experiments show that AIMA reduces similarity scores by up to 35.8%in state-of-the-art BCSD models.When incorporated into training data,it also enhances model robustness,achieving a 5.9%improvement in AUROC.展开更多
With respect to oceanic fluid dynamics,certain models have appeared,e.g.,an extended time-dependent(3+1)-dimensional shallow water wave equation in an ocean or a river,which we investigate in this paper.Using symbolic...With respect to oceanic fluid dynamics,certain models have appeared,e.g.,an extended time-dependent(3+1)-dimensional shallow water wave equation in an ocean or a river,which we investigate in this paper.Using symbolic computation,we find out,on one hand,a set of bilinear auto-Backlund transformations,which could connect certain solutions of that equation with other solutions of that equation itself,and on the other hand,a set of similarity reductions,which could go from that equation to a known ordinary differential equation.The results in this paper depend on all the oceanic variable coefficients in that equation.展开更多
Due to the numerous variables to take into account as well as the inherent ambiguity and uncertainty,evaluating educational institutions can be difficult.The concept of a possibility Pythagorean fuzzy hypersoft set(pP...Due to the numerous variables to take into account as well as the inherent ambiguity and uncertainty,evaluating educational institutions can be difficult.The concept of a possibility Pythagorean fuzzy hypersoft set(pPyFHSS)is more flexible in this regard than other theoretical fuzzy set-like models,even though some attempts have been made in the literature to address such uncertainties.This study investigates the elementary notions of pPyFHSS including its set-theoretic operations union,intersection,complement,OR-and AND-operations.Some results related to these operations are also modified for pPyFHSS.Additionally,the similarity measures between pPyFHSSs are formulated with the assistance of numerical examples and results.Lastly,an intelligent decision-assisted mechanism is developed with the proposal of a robust algorithm based on similarity measures for solving multi-attribute decision-making(MADM)problems.A case study that helps the decision-makers assess the best educational institution is discussed to validate the suggested system.The algorithmic results are compared with the most pertinent model to evaluate the adaptability of pPyFHSS,as it generalizes the classical possibility fuzzy set-like theoretical models.Similarly,while considering significant evaluating factors,the flexibility of pPyFHSS is observed through structural comparison.展开更多
Physical analog modeling is an effective approach for studying the hazards of coal bursts in coal similarity criteria for physical and mechanical parameters of the actual and similar materials are crucial to yield rea...Physical analog modeling is an effective approach for studying the hazards of coal bursts in coal similarity criteria for physical and mechanical parameters of the actual and similar materials are crucial to yield realistic results.The derivation of similarity criteria is predominantly based on dimensional analysis,while a systematic methodology has yet to be developed.This paper attempts to fill this gap by combining the equation transformation method with similarity theory to conduct an in-depth study on the similarity criteria of physical parameters of impact coal with various internal block sizes.On this basis,the influence of internal block size of impact coal on similarity criteria was studied.Block size can provide a selection basis for similar materials,and the influence of block size on model physical parameters and similarity criteria under different geometric similarity ratios was explored.The variation laws between geometric similarity ratio,block size,and physical properties were clarified,and the similarity criteria of impact coal under the influence of block size were adjusted.New insights into material selection for physical analog modeling were proposed.The established similarity criteria for impact coal under the influence of different block sizes can provide a theoretical basis for determining various parameters in the physical analog modeling of coal bursts,when building a physical model of impact coal,material selection and size selection can be based on similarity criteria to more accurately reproduce coal explosion disasters in the laboratory.展开更多
To enhance network security,this study employs a deep graph matching model for vulnerability similarity detection.The model utilizes a Word Embedding layer to vectorize data words,an Image Embedding layer to vectorize...To enhance network security,this study employs a deep graph matching model for vulnerability similarity detection.The model utilizes a Word Embedding layer to vectorize data words,an Image Embedding layer to vectorize data graphs,and an LSTM layer to extract the associations between word and graph vectors.A Dropout layer is applied to randomly deactivate neurons in the LSTM layer,while a Softmax layer maps the LSTM analysis results.Finally,a fully connected layer outputs the detection results with a dimension of 1.Experimental results demonstrate that the AUC of the deep graph matching vulnerability similarity detection model is 0.9721,indicating good stability.The similarity scores for vulnerabilities such as memory leaks,buffer overflows,and targeted attacks are close to 1,showing significant similarity.In contrast,the similarity scores for vulnerabilities like out-of-bounds memory access and logical design flaws are less than 0.4,indicating good similarity detection performance.The model’s evaluation metrics are all above 97%,with high detection accuracy,which is beneficial for improving network security.展开更多
Graph similarity learning aims to calculate the similarity between pairs of graphs.Existing unsupervised graph similarity learning methods based on contrastive learning encounter challenges related to random graph aug...Graph similarity learning aims to calculate the similarity between pairs of graphs.Existing 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 subgraphs.To address these issues,we propose a graph similarity learning model based on learnable augmentation and multi-level contrastive learning.First,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 graph.To enhance contrastive levels,we employ a biased random walk method to generate corresponding subgraphs,enriching the contrastive hierarchy.Second,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 graph.The goal is to maximize node consistency between different views and learn node matching between different graphs,resulting in node-level representations for each graph.Subgraph representations are then obtained through pooling operations,and we conduct contrastive learning utilizing both node and subgraph representations.Finally,the graph similarity score is computed according to different downstream tasks.We 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 levels.Additionally,the model achieves the best overall performance.展开更多
This study presents a detailed experimental evaluation of a newly developed mechanistic scale-up methodology for gas-solid fluidized beds.Traditional scale-up approaches typically rely on matching global dimensionless...This study presents a detailed experimental evaluation of a newly developed mechanistic scale-up methodology for gas-solid fluidized beds.Traditional scale-up approaches typically rely on matching global dimensionless groups,which often fail to ensure local hydrodynamic similarity.In contrast,the new mechanistic method aims to achieve scale-up by matching the radial profiles of gas holdup between geometrically similar beds at corresponding dimensionless axial positions(z/Dc).This approach is based on the premise that when gas holdup profiles align,other key hydrodynamic parameters—such as solids holdup and particle velocity—also become similar.To validate this methodology,experiments were conducted in two fluidized beds with inner diameters of 14 cm and 44 cm.Optical probes and gamma ray densitometry(GRD)were used to measure local gas holdup,solids holdup,and particle velocity at multiple axial and radial positions.The results show that matched gas holdup profiles led to mean absolute deviations(MAD)below 3%in solids holdup and particle velocity,confirming hydrodynamic similarity.In contrast,unmatched profiles resulted in significant deviations across all parameters.展开更多
Few-shot learning has emerged as a crucial technique for coral species classification,addressing the challenge of limited labeled data in underwater environments.This study introduces an optimized few-shot learning mo...Few-shot learning has emerged as a crucial technique for coral species classification,addressing the challenge of limited labeled data in underwater environments.This study introduces an optimized few-shot learning model that enhances classification accuracy while minimizing reliance on extensive data collection.The proposed model integrates a hybrid similarity measure combining Euclidean distance and cosine similarity,effectively capturing both feature magnitude and directional relationships.This approach achieves a notable accuracy of 71.8%under a 5-way 5-shot evaluation,outperforming state-of-the-art models such as Prototypical Networks,FEAT,and ESPT by up to 10%.Notably,the model demonstrates high precision in classifying Siderastreidae(87.52%)and Fungiidae(88.95%),underscoring its effectiveness in distinguishing subtle morphological differences.To further enhance performance,we incorporate a self-supervised learning mechanism based on contrastive learning,enabling the model to extract robust representations by leveraging local structural patterns in corals.This enhancement significantly improves classification accuracy,particularly for species with high intra-class variation,leading to an overall accuracy of 76.52%under a 5-way 10-shot evaluation.Additionally,the model exploits the repetitive structures inherent in corals,introducing a local feature aggregation strategy that refines classification through spatial information integration.Beyond its technical contributions,this study presents a scalable and efficient approach for automated coral reef monitoring,reducing annotation costs while maintaining high classification accuracy.By improving few-shot learning performance in underwater environments,our model enhances monitoring accuracy by up to 15%compared to traditional methods,offering a practical solution for large-scale coral conservation efforts.展开更多
This study presents a new approach that advances the algorithm of similarity measures between generalized fuzzy numbers. Following a brief introduction to some properties of the proposed method, a comparative analysis...This study presents a new approach that advances the algorithm of similarity measures between generalized fuzzy numbers. Following a brief introduction to some properties of the proposed method, a comparative analysis based on 36 sets of generalized fuzzy numbers was performed, in which the degree of similarity of the fuzzy numbers was calculated with the proposed method and seven methods established by previous studies in the literature. The results of the analytical comparison show that the proposed similarity outperforms the existing methods by overcoming their drawbacks and yielding accurate outcomes in all calculations of similarity measures under consideration. Finally, in a numerical example that involves recommending cars to customers based on a nine-member linguistic term set, the proposed similarity measure proves to be competent in addressing fuzzy number recommendation problems.展开更多
Binary Code Similarity Detection(BCSD)is vital for vulnerability discovery,malware detection,and software security,especially when source code is unavailable.Yet,it faces challenges from semantic loss,recompilation va...Binary Code Similarity Detection(BCSD)is vital for vulnerability discovery,malware detection,and software security,especially when source code is unavailable.Yet,it faces challenges from semantic loss,recompilation variations,and obfuscation.Recent advances in artificial intelligence—particularly natural language processing(NLP),graph representation learning(GRL),and large language models(LLMs)—have markedly improved accuracy,enabling better recognition of code variants and deeper semantic understanding.This paper presents a comprehensive review of 82 studies published between 1975 and 2025,systematically tracing the historical evolution of BCSD and analyzing the progressive incorporation of artificial intelligence(AI)techniques.Particular emphasis is placed on the role of LLMs,which have recently emerged as transformative tools in advancing semantic representation and enhancing detection performance.The review is organized around five central research questions:(1)the chronological development and milestones of BCSD;(2)the construction of AI-driven technical roadmaps that chart methodological transitions;(3)the design and implementation of general analytical workflows for binary code analysis;(4)the applicability,strengths,and limitations of LLMs in capturing semantic and structural features of binary code;and(5)the persistent challenges and promising directions for future investigation.By synthesizing insights across these dimensions,the study demonstrates how LLMs reshape the landscape of binary code analysis,offering unprecedented opportunities to improve accuracy,scalability,and adaptability in real-world scenarios.This review not only bridges a critical gap in the existing literature but also provides a forward-looking perspective,serving as a valuable reference for researchers and practitioners aiming to advance AI-powered BCSD methodologies and applications.展开更多
Similarity has been playing an important role in computer science,artificial intelligence(AI)and data science.However,similarity intelligence has been ignored in these disciplines.Similarity intelligence is a process ...Similarity has been playing an important role in computer science,artificial intelligence(AI)and data science.However,similarity intelligence has been ignored in these disciplines.Similarity intelligence is a process of discovering intelligence through similarity.This article will explore similarity intelligence,similarity-based reasoning,similarity computing and analytics.More specifically,this article looks at the similarity as an intelligence and its impact on a few areas in the real world.It explores similarity intelligence accompanying experience-based intelligence,knowledge-based intelligence,and data-based intelligence to play an important role in computer science,AI,and data science.This article explores similarity-based reasoning(SBR)and proposes three similarity-based inference rules.It then examines similarity computing and analytics,and a multiagent SBR system.The main contributions of this article are:1)Similarity intelligence is discovered from experience-based intelligence consisting of data-based intelligence and knowledge-based intelligence.2)Similarity-based reasoning,computing and analytics can be used to create similarity intelligence.The proposed approach will facilitate research and development of similarity intelligence,similarity computing and analytics,machine learning and case-based reasoning.展开更多
Recommendation systems are going to be an integral part of any E-Business in near future.As in any other E-business,recommendation systems also play a key role in the travel business where the user has to be recommend...Recommendation systems are going to be an integral part of any E-Business in near future.As in any other E-business,recommendation systems also play a key role in the travel business where the user has to be recommended with a restaurant that best suits him.In general,the recommendations to a user are made based on similarity that exists between the intended user and the other users.This similarity can be calculated either based on the similarity between the user profiles or the similarity between the ratings made by the users.First phase of this work concentrates on experimentally analyzing both these models and get a deep insight of these models.With the lessons learned from the insights,second phase of the work concentrates on developing a deep learning model.The model does not depend on the other user's profile or rating made by them.The model is tested with a small restaurant dataset and the model can predict whether a user likes the restaurant or not.The model is trained with different users and their rating.The system learns from it and in order to predict whether a new user likes or not a restaurant that he/she has not visited earlier,all the data the trained model needed is the rating made by the same user for different restaurants.The model is deployed in a cloud environment in order to extend it to be more realistic product in future.Result evaluated with dataset,it achieves 74.6%is accurate prediction of results,where as existing techniques achieves only 64%.展开更多
Liquid metal filling flow process in the microscale during the centrifugal casting process was studied by means of similar physical simulation. The research was focused on derived similarity criterion. Based on the tr...Liquid metal filling flow process in the microscale during the centrifugal casting process was studied by means of similar physical simulation. The research was focused on derived similarity criterion. Based on the traditional flow equations, the flow equation and the Bernoulli＇s equation for liquid metal flows in micro-scale space were derived, which provides a mathematical model for numerical simulation of micro-scale flow. In the meanwhile, according to the micro-flow equation and the similarity theory, the similarity criterion for the physical simulation of the mold filling behaviors was presented under centrifugal force field, so as to achieve the visual observation and quantitative analysis of micro-flow process.展开更多
An estimation method for aircraft similarity based on fuzzy theory and grey incidence analysis is presented. This estimation method is made up of the triangular fuzzy transforming model of linguistic variables and the...An estimation method for aircraft similarity based on fuzzy theory and grey incidence analysis is presented. This estimation method is made up of the triangular fuzzy transforming model of linguistic variables and the method of grey incidence analysis. Nine feature attributes of aircraft are selected to estimate the similarity between the new aircraft and the existing aircraft. A new aircraft X and other six existing aircrafts are taken as examples. Analyses show that similarity estimation results obtained from the method are in accordance with practice.展开更多
In order to achieve adaptive and efficient service composition, a task-oriented algorithm for discovering services is proposed. The traditional process of service composition is divided into semantic discovery and fun...In order to achieve adaptive and efficient service composition, a task-oriented algorithm for discovering services is proposed. The traditional process of service composition is divided into semantic discovery and functional matching and makes tasks be operation objects. Semantic similarity is used to discover services matching a specific task and then generate a corresponding task-oriented web service composition （TWC） graph. Moreover, an algorithm for the new service is designed to update the TWC. The approach is applied to the composition model, in which the TWC is searched to obtain an optimal path and the final service composition is output. Also, the model can implement realtime updating with changing environments. Experimental results demonstrate the feasibility and effectiveness of the algorithm and indicate that the maximum searching radius can be set to 2 to achieve an equilibrium point of quality and quantity.展开更多
The concept of the degree of similarity between interval-valued intuitionistic fuzzy sets （IVIFSs） is introduced, and some distance measures between IVIFSs are defined based on the Hamming distance, the normalized H...The concept of the degree of similarity between interval-valued intuitionistic fuzzy sets （IVIFSs） is introduced, and some distance measures between IVIFSs are defined based on the Hamming distance, the normalized Hamming distance, the weighted Hamming distance, the Euclidean distance, the normalized Euclidean distance, and the weighted Euclidean distance, etc. Then, by combining the Hausdorff metric with the Hamming distance, the Euclidean distance and their weighted versions, two other similarity measures between IVIFSs, i. e., the weighted Hamming distance based on the Hausdorff metric and the weighted Euclidean distance based on the Hausdorff metric, are defined, and then some of their properties are studied. Finally, based on these distance measures, some similarity measures between IVIFSs are defined, and the similarity measures are applied to pattern recognitions with interval-valued intuitionistic fuzzy information.展开更多
A method that combines category-based and keyword-based concepts for a better information retrieval system is introduced. To improve document clustering, a document similarity measure based on cosine vector and keywor...A method that combines category-based and keyword-based concepts for a better information retrieval system is introduced. To improve document clustering, a document similarity measure based on cosine vector and keywords frequency in documents is proposed, but also with an input ontology. The ontology is domain specific and includes a list of keywords organized by degree of importance to the categories of the ontology, and by means of semantic knowledge, the ontology can improve the effects of document similarity measure and feedback of information retrieval systems. Two approaches to evaluating the performance of this similarity measure and the comparison with standard cosine vector similarity measure are also described.展开更多
The sea bottom in front of a breakwater is scoured under the action of broken waves,and this will affect the stability of the breakwater.In this paper,the scours of sandy seabed in front of a breakwater under the acti...The sea bottom in front of a breakwater is scoured under the action of broken waves,and this will affect the stability of the breakwater.In this paper,the scours of sandy seabed in front of a breakwater under the action of broken waves are investigated experimentally.The depth and range of the scouring trough at the foot of a breakwater are studied,and the influence of open foundation-bed on scouring and depositing is also discussed.In order to apply the research results to practical projects,the scale of model sediment and the scale of scours and depositions are suggested.展开更多
Services discovery based on syntactic matching cannot adapt to the open and dynamic environment of the web. To select the proper one from the web services candidate set provided by syntactic matching, a service select...Services discovery based on syntactic matching cannot adapt to the open and dynamic environment of the web. To select the proper one from the web services candidate set provided by syntactic matching, a service selection method based on semantic similarity is proposed. First, this method defines a web services ontology including QoS and context as semantic supporting, which also provides a set of terms to describe the interfaces of web services. Secondly, the similarity degree of two web services is evaluated by computing the semantic distances of those terms used to describe interfaces. Compared with existing methods, interfaces of web services can be interpreted under ontology, because it provides a formal and semantic specification of conceptualization. Meanwhile, efficiency and accuracy of services selection are improved.展开更多
The homogeneous balance method, which is simple and straightforward, is extended to seek for Backlund transformation, exact bell shape soliton solutions and similarity reduction of the Boussinesq equation. The method...The homogeneous balance method, which is simple and straightforward, is extended to seek for Backlund transformation, exact bell shape soliton solutions and similarity reduction of the Boussinesq equation. The method can be used in general.展开更多
基金supported by Key Laboratory of Cyberspace Security,Ministry of Education,China。
文摘Transformer-based models have significantly advanced binary code similarity detection(BCSD)by leveraging their semantic encoding capabilities for efficient function matching across diverse compilation settings.Although adversarial examples can strategically undermine the accuracy of BCSD models and protect critical code,existing techniques predominantly depend on inserting artificial instructions,which incur high computational costs and offer limited diversity of perturbations.To address these limitations,we propose AIMA,a novel gradient-guided assembly instruction relocation method.Our method decouples the detection model into tokenization,embedding,and encoding layers to enable efficient gradient computation.Since token IDs of instructions are discrete and nondifferentiable,we compute gradients in the continuous embedding space to evaluate the influence of each token.The most critical tokens are identified by calculating the L2 norm of their embedding gradients.We then establish a mapping between instructions and their corresponding tokens to aggregate token-level importance into instructionlevel significance.To maximize adversarial impact,a sliding window algorithm selects the most influential contiguous segments for relocation,ensuring optimal perturbation with minimal length.This approach efficiently locates critical code regions without expensive search operations.The selected segments are relocated outside their original function boundaries via a jump mechanism,which preserves runtime control flow and functionality while introducing“deletion”effects in the static instruction sequence.Extensive experiments show that AIMA reduces similarity scores by up to 35.8%in state-of-the-art BCSD models.When incorporated into training data,it also enhances model robustness,achieving a 5.9%improvement in AUROC.
基金financially supported by the Scientific Research Foundation of North China University of Technology(Grant Nos.11005136024XN147-87 and 110051360024XN151-86).
文摘With respect to oceanic fluid dynamics,certain models have appeared,e.g.,an extended time-dependent(3+1)-dimensional shallow water wave equation in an ocean or a river,which we investigate in this paper.Using symbolic computation,we find out,on one hand,a set of bilinear auto-Backlund transformations,which could connect certain solutions of that equation with other solutions of that equation itself,and on the other hand,a set of similarity reductions,which could go from that equation to a known ordinary differential equation.The results in this paper depend on all the oceanic variable coefficients in that equation.
基金supported by the Deanship of Graduate Studies and Scientific Research at Qassim University(QU-APC-2024-9/1).
文摘Due to the numerous variables to take into account as well as the inherent ambiguity and uncertainty,evaluating educational institutions can be difficult.The concept of a possibility Pythagorean fuzzy hypersoft set(pPyFHSS)is more flexible in this regard than other theoretical fuzzy set-like models,even though some attempts have been made in the literature to address such uncertainties.This study investigates the elementary notions of pPyFHSS including its set-theoretic operations union,intersection,complement,OR-and AND-operations.Some results related to these operations are also modified for pPyFHSS.Additionally,the similarity measures between pPyFHSSs are formulated with the assistance of numerical examples and results.Lastly,an intelligent decision-assisted mechanism is developed with the proposal of a robust algorithm based on similarity measures for solving multi-attribute decision-making(MADM)problems.A case study that helps the decision-makers assess the best educational institution is discussed to validate the suggested system.The algorithmic results are compared with the most pertinent model to evaluate the adaptability of pPyFHSS,as it generalizes the classical possibility fuzzy set-like theoretical models.Similarly,while considering significant evaluating factors,the flexibility of pPyFHSS is observed through structural comparison.
基金supported by the Fundamental Research Funds for the Central Universities(No.2024-10941)China University of Mining and Technology 2024 Graduate Innovation Program Projects(No.2024WLKXJ011)+1 种基金Jiangsu Graduate Student Research and Innovation Program(No.KYCX24_2846)the National Natural Science Foundation of China(Nos.52227901 and 51934007).
文摘Physical analog modeling is an effective approach for studying the hazards of coal bursts in coal similarity criteria for physical and mechanical parameters of the actual and similar materials are crucial to yield realistic results.The derivation of similarity criteria is predominantly based on dimensional analysis,while a systematic methodology has yet to be developed.This paper attempts to fill this gap by combining the equation transformation method with similarity theory to conduct an in-depth study on the similarity criteria of physical parameters of impact coal with various internal block sizes.On this basis,the influence of internal block size of impact coal on similarity criteria was studied.Block size can provide a selection basis for similar materials,and the influence of block size on model physical parameters and similarity criteria under different geometric similarity ratios was explored.The variation laws between geometric similarity ratio,block size,and physical properties were clarified,and the similarity criteria of impact coal under the influence of block size were adjusted.New insights into material selection for physical analog modeling were proposed.The established similarity criteria for impact coal under the influence of different block sizes can provide a theoretical basis for determining various parameters in the physical analog modeling of coal bursts,when building a physical model of impact coal,material selection and size selection can be based on similarity criteria to more accurately reproduce coal explosion disasters in the laboratory.
基金Special Project Funded by Tsinghua University Press:“Engineering Drawing and CAD”Course Construction and Textbook Development。
文摘To enhance network security,this study employs a deep graph matching model for vulnerability similarity detection.The model utilizes a Word Embedding layer to vectorize data words,an Image Embedding layer to vectorize data graphs,and an LSTM layer to extract the associations between word and graph vectors.A Dropout layer is applied to randomly deactivate neurons in the LSTM layer,while a Softmax layer maps the LSTM analysis results.Finally,a fully connected layer outputs the detection results with a dimension of 1.Experimental results demonstrate that the AUC of the deep graph matching vulnerability similarity detection model is 0.9721,indicating good stability.The similarity scores for vulnerabilities such as memory leaks,buffer overflows,and targeted attacks are close to 1,showing significant similarity.In contrast,the similarity scores for vulnerabilities like out-of-bounds memory access and logical design flaws are less than 0.4,indicating good similarity detection performance.The model’s evaluation metrics are all above 97%,with high detection accuracy,which is beneficial for improving network security.
文摘Graph similarity learning aims to calculate the similarity between pairs of graphs.Existing 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 subgraphs.To address these issues,we propose a graph similarity learning model based on learnable augmentation and multi-level contrastive learning.First,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 graph.To enhance contrastive levels,we employ a biased random walk method to generate corresponding subgraphs,enriching the contrastive hierarchy.Second,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 graph.The goal is to maximize node consistency between different views and learn node matching between different graphs,resulting in node-level representations for each graph.Subgraph representations are then obtained through pooling operations,and we conduct contrastive learning utilizing both node and subgraph representations.Finally,the graph similarity score is computed according to different downstream tasks.We 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 levels.Additionally,the model achieves the best overall performance.
文摘This study presents a detailed experimental evaluation of a newly developed mechanistic scale-up methodology for gas-solid fluidized beds.Traditional scale-up approaches typically rely on matching global dimensionless groups,which often fail to ensure local hydrodynamic similarity.In contrast,the new mechanistic method aims to achieve scale-up by matching the radial profiles of gas holdup between geometrically similar beds at corresponding dimensionless axial positions(z/Dc).This approach is based on the premise that when gas holdup profiles align,other key hydrodynamic parameters—such as solids holdup and particle velocity—also become similar.To validate this methodology,experiments were conducted in two fluidized beds with inner diameters of 14 cm and 44 cm.Optical probes and gamma ray densitometry(GRD)were used to measure local gas holdup,solids holdup,and particle velocity at multiple axial and radial positions.The results show that matched gas holdup profiles led to mean absolute deviations(MAD)below 3%in solids holdup and particle velocity,confirming hydrodynamic similarity.In contrast,unmatched profiles resulted in significant deviations across all parameters.
基金funded by theNational Science and TechnologyCouncil(NSTC),Taiwan,under grant numbers NSTC 112-2634-F-019-001 and NSTC 113-2634-F-A49-007.
文摘Few-shot learning has emerged as a crucial technique for coral species classification,addressing the challenge of limited labeled data in underwater environments.This study introduces an optimized few-shot learning model that enhances classification accuracy while minimizing reliance on extensive data collection.The proposed model integrates a hybrid similarity measure combining Euclidean distance and cosine similarity,effectively capturing both feature magnitude and directional relationships.This approach achieves a notable accuracy of 71.8%under a 5-way 5-shot evaluation,outperforming state-of-the-art models such as Prototypical Networks,FEAT,and ESPT by up to 10%.Notably,the model demonstrates high precision in classifying Siderastreidae(87.52%)and Fungiidae(88.95%),underscoring its effectiveness in distinguishing subtle morphological differences.To further enhance performance,we incorporate a self-supervised learning mechanism based on contrastive learning,enabling the model to extract robust representations by leveraging local structural patterns in corals.This enhancement significantly improves classification accuracy,particularly for species with high intra-class variation,leading to an overall accuracy of 76.52%under a 5-way 10-shot evaluation.Additionally,the model exploits the repetitive structures inherent in corals,introducing a local feature aggregation strategy that refines classification through spatial information integration.Beyond its technical contributions,this study presents a scalable and efficient approach for automated coral reef monitoring,reducing annotation costs while maintaining high classification accuracy.By improving few-shot learning performance in underwater environments,our model enhances monitoring accuracy by up to 15%compared to traditional methods,offering a practical solution for large-scale coral conservation efforts.
文摘This study presents a new approach that advances the algorithm of similarity measures between generalized fuzzy numbers. Following a brief introduction to some properties of the proposed method, a comparative analysis based on 36 sets of generalized fuzzy numbers was performed, in which the degree of similarity of the fuzzy numbers was calculated with the proposed method and seven methods established by previous studies in the literature. The results of the analytical comparison show that the proposed similarity outperforms the existing methods by overcoming their drawbacks and yielding accurate outcomes in all calculations of similarity measures under consideration. Finally, in a numerical example that involves recommending cars to customers based on a nine-member linguistic term set, the proposed similarity measure proves to be competent in addressing fuzzy number recommendation problems.
文摘Binary Code Similarity Detection(BCSD)is vital for vulnerability discovery,malware detection,and software security,especially when source code is unavailable.Yet,it faces challenges from semantic loss,recompilation variations,and obfuscation.Recent advances in artificial intelligence—particularly natural language processing(NLP),graph representation learning(GRL),and large language models(LLMs)—have markedly improved accuracy,enabling better recognition of code variants and deeper semantic understanding.This paper presents a comprehensive review of 82 studies published between 1975 and 2025,systematically tracing the historical evolution of BCSD and analyzing the progressive incorporation of artificial intelligence(AI)techniques.Particular emphasis is placed on the role of LLMs,which have recently emerged as transformative tools in advancing semantic representation and enhancing detection performance.The review is organized around five central research questions:(1)the chronological development and milestones of BCSD;(2)the construction of AI-driven technical roadmaps that chart methodological transitions;(3)the design and implementation of general analytical workflows for binary code analysis;(4)the applicability,strengths,and limitations of LLMs in capturing semantic and structural features of binary code;and(5)the persistent challenges and promising directions for future investigation.By synthesizing insights across these dimensions,the study demonstrates how LLMs reshape the landscape of binary code analysis,offering unprecedented opportunities to improve accuracy,scalability,and adaptability in real-world scenarios.This review not only bridges a critical gap in the existing literature but also provides a forward-looking perspective,serving as a valuable reference for researchers and practitioners aiming to advance AI-powered BCSD methodologies and applications.
文摘Similarity has been playing an important role in computer science,artificial intelligence(AI)and data science.However,similarity intelligence has been ignored in these disciplines.Similarity intelligence is a process of discovering intelligence through similarity.This article will explore similarity intelligence,similarity-based reasoning,similarity computing and analytics.More specifically,this article looks at the similarity as an intelligence and its impact on a few areas in the real world.It explores similarity intelligence accompanying experience-based intelligence,knowledge-based intelligence,and data-based intelligence to play an important role in computer science,AI,and data science.This article explores similarity-based reasoning(SBR)and proposes three similarity-based inference rules.It then examines similarity computing and analytics,and a multiagent SBR system.The main contributions of this article are:1)Similarity intelligence is discovered from experience-based intelligence consisting of data-based intelligence and knowledge-based intelligence.2)Similarity-based reasoning,computing and analytics can be used to create similarity intelligence.The proposed approach will facilitate research and development of similarity intelligence,similarity computing and analytics,machine learning and case-based reasoning.
文摘Recommendation systems are going to be an integral part of any E-Business in near future.As in any other E-business,recommendation systems also play a key role in the travel business where the user has to be recommended with a restaurant that best suits him.In general,the recommendations to a user are made based on similarity that exists between the intended user and the other users.This similarity can be calculated either based on the similarity between the user profiles or the similarity between the ratings made by the users.First phase of this work concentrates on experimentally analyzing both these models and get a deep insight of these models.With the lessons learned from the insights,second phase of the work concentrates on developing a deep learning model.The model does not depend on the other user's profile or rating made by them.The model is tested with a small restaurant dataset and the model can predict whether a user likes the restaurant or not.The model is trained with different users and their rating.The system learns from it and in order to predict whether a new user likes or not a restaurant that he/she has not visited earlier,all the data the trained model needed is the rating made by the same user for different restaurants.The model is deployed in a cloud environment in order to extend it to be more realistic product in future.Result evaluated with dataset,it achieves 74.6%is accurate prediction of results,where as existing techniques achieves only 64%.
基金Project(51005053)supported by the National Science Foundation for Young Scientists of China
文摘Liquid metal filling flow process in the microscale during the centrifugal casting process was studied by means of similar physical simulation. The research was focused on derived similarity criterion. Based on the traditional flow equations, the flow equation and the Bernoulli＇s equation for liquid metal flows in micro-scale space were derived, which provides a mathematical model for numerical simulation of micro-scale flow. In the meanwhile, according to the micro-flow equation and the similarity theory, the similarity criterion for the physical simulation of the mold filling behaviors was presented under centrifugal force field, so as to achieve the visual observation and quantitative analysis of micro-flow process.
文摘An estimation method for aircraft similarity based on fuzzy theory and grey incidence analysis is presented. This estimation method is made up of the triangular fuzzy transforming model of linguistic variables and the method of grey incidence analysis. Nine feature attributes of aircraft are selected to estimate the similarity between the new aircraft and the existing aircraft. A new aircraft X and other six existing aircrafts are taken as examples. Analyses show that similarity estimation results obtained from the method are in accordance with practice.
基金The National Key Technology R&D Program of Chinaduring the 11th Five-Year Plan Period(No2007BAF23B0302)the Major Research Plan of the National Natural Science Foundation of China(No90818028)
文摘In order to achieve adaptive and efficient service composition, a task-oriented algorithm for discovering services is proposed. The traditional process of service composition is divided into semantic discovery and functional matching and makes tasks be operation objects. Semantic similarity is used to discover services matching a specific task and then generate a corresponding task-oriented web service composition （TWC） graph. Moreover, an algorithm for the new service is designed to update the TWC. The approach is applied to the composition model, in which the TWC is searched to obtain an optimal path and the final service composition is output. Also, the model can implement realtime updating with changing environments. Experimental results demonstrate the feasibility and effectiveness of the algorithm and indicate that the maximum searching radius can be set to 2 to achieve an equilibrium point of quality and quantity.
基金The National Natural Science Foundation of China (No70571087)the National Science Fund for Distinguished Young Scholarsof China (No70625005)
文摘The concept of the degree of similarity between interval-valued intuitionistic fuzzy sets （IVIFSs） is introduced, and some distance measures between IVIFSs are defined based on the Hamming distance, the normalized Hamming distance, the weighted Hamming distance, the Euclidean distance, the normalized Euclidean distance, and the weighted Euclidean distance, etc. Then, by combining the Hausdorff metric with the Hamming distance, the Euclidean distance and their weighted versions, two other similarity measures between IVIFSs, i. e., the weighted Hamming distance based on the Hausdorff metric and the weighted Euclidean distance based on the Hausdorff metric, are defined, and then some of their properties are studied. Finally, based on these distance measures, some similarity measures between IVIFSs are defined, and the similarity measures are applied to pattern recognitions with interval-valued intuitionistic fuzzy information.
基金The Young Teachers Scientific Research Foundation (YTSRF) of Nanjing University of Science and Technology in the Year of2005-2006.
文摘A method that combines category-based and keyword-based concepts for a better information retrieval system is introduced. To improve document clustering, a document similarity measure based on cosine vector and keywords frequency in documents is proposed, but also with an input ontology. The ontology is domain specific and includes a list of keywords organized by degree of importance to the categories of the ontology, and by means of semantic knowledge, the ontology can improve the effects of document similarity measure and feedback of information retrieval systems. Two approaches to evaluating the performance of this similarity measure and the comparison with standard cosine vector similarity measure are also described.
基金the National Natural Science Foundation of China!(No.599790 1 9)
文摘The sea bottom in front of a breakwater is scoured under the action of broken waves,and this will affect the stability of the breakwater.In this paper,the scours of sandy seabed in front of a breakwater under the action of broken waves are investigated experimentally.The depth and range of the scouring trough at the foot of a breakwater are studied,and the influence of open foundation-bed on scouring and depositing is also discussed.In order to apply the research results to practical projects,the scale of model sediment and the scale of scours and depositions are suggested.
基金The National Natural Science Foundation of China(No.70471090,70472005),the Natural Science Foundation of Jiangsu Province(No.BK2004052,BK2005046).
文摘Services discovery based on syntactic matching cannot adapt to the open and dynamic environment of the web. To select the proper one from the web services candidate set provided by syntactic matching, a service selection method based on semantic similarity is proposed. First, this method defines a web services ontology including QoS and context as semantic supporting, which also provides a set of terms to describe the interfaces of web services. Secondly, the similarity degree of two web services is evaluated by computing the semantic distances of those terms used to describe interfaces. Compared with existing methods, interfaces of web services can be interpreted under ontology, because it provides a formal and semantic specification of conceptualization. Meanwhile, efficiency and accuracy of services selection are improved.
文摘The homogeneous balance method, which is simple and straightforward, is extended to seek for Backlund transformation, exact bell shape soliton solutions and similarity reduction of the Boussinesq equation. The method can be used in general.
