• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.5
• /
• pp.205-212
• /
• 2019

Scene graph is a kind of knowledge graph that represents both objects and their relationships found in a image. This paper proposes a 3D scene graph generation model for three-dimensional indoor environments. An 3D scene graph includes not only object types, their positions and attributes, but also three-dimensional spatial relationships between them, An 3D scene graph can be viewed as a prior knowledge base describing the given environment within that the agent will be deployed later. Therefore, 3D scene graphs can be used in many useful applications, such as visual question answering (VQA) and service robots. This proposed 3D scene graph generation model consists of four sub-networks: object detection network (ObjNet), attribute prediction network (AttNet), transfer network (TransNet), relationship prediction network (RelNet). Conducting several experiments with 3D simulated indoor environments provided by AI2-THOR, we confirmed that the proposed model shows high performance.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.7
• /
• pp.61-69
• /
• 2019

In this paper, a classification method of random graph models is proposed and it is based on centralities of the random graphs. Similarity between two random graphs is measured for the classification of random graph models. The similarity between two random graph models $G^{R_1}$ and $G^{R_2}$ is defined by the distance of $G^{R_1}$ and $G^{R_2}$, where $G^{R_2}$ is a set of random graph $G^{R_2}=\{G_1^{R_2},...,G_p^{R_2}\}$ that have the same number of nodes and edges as random graph $G^{R_1}$. The distance($G^{R_1},G^{R_2}$) is obtained by comparing centralities of $G^{R_1}$ and $G^{R_2}$. Through the computational experiments, we show that it is possible to compare random graph models regardless of the number of vertices or edges of the random graphs. Also, it is possible to identify and classify the properties of the random graph models by measuring and comparing similarities between random graph models.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.8
• /
• pp.2101-2123
• /
• 2023

Recent studies have shown that the neural network-based binary code similarity detection technology performs well in vulnerability mining, plagiarism detection, and malicious code analysis. However, existing cross-architecture methods still suffer from insufficient feature characterization and low discrimination accuracy. To address these issues, this paper proposes a cross-architecture binary function similarity detection method based on composite feature model (SDCFM). Firstly, the binary function is converted into vector representation according to the proposed composite feature model, which is composed of instruction statistical features, control flow graph structural features, and application program interface calling behavioral features. Then, the composite features are embedded by the proposed hierarchical embedding network based on a graph neural network. In which, the block-level features and the function-level features are processed separately and finally fused into the embedding. In addition, to make the trained model more accurate and stable, our method utilizes the embeddings of predecessor nodes to modify the node embedding in the iterative updating process of the graph neural network. To assess the effectiveness of composite feature model, we contrast SDCFM with the state of art method on benchmark datasets. The experimental results show that SDCFM has good performance both on the area under the curve in the binary function similarity detection task and the vulnerable candidate function ranking in vulnerability search task.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.1
• /
• pp.649-654
• /
• 2023

This paper proposes the design of a neural network structure search model using graph convolutional neural networks. Deep learning has a problem of not being able to verify whether the designed model has a structure with optimized performance due to the nature of learning as a black box. The neural network structure search model is composed of a recurrent neural network that creates a model and a convolutional neural network that is the generated network. Conventional neural network structure search models use recurrent neural networks, but in this paper, we propose GC-NAS, which uses graph convolutional neural networks instead of recurrent neural networks to create convolutional neural network models. The proposed GC-NAS uses the Layer Extraction Block to explore depth, and the Hyper Parameter Prediction Block to explore spatial and temporal information (hyper parameters) based on depth information in parallel. Therefore, since the depth information is reflected, the search area is wider, and the purpose of the search area of the model is clear by conducting a parallel search with depth information, so it is judged to be superior in theoretical structure compared to GC-NAS. GC-NAS is expected to solve the problem of the high-dimensional time axis and the range of spatial search of recurrent neural networks in the existing neural network structure search model through the graph convolutional neural network block and graph generation algorithm. In addition, we hope that the GC-NAS proposed in this paper will serve as an opportunity for active research on the application of graph convolutional neural networks to neural network structure search.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2010.04a
• /
• pp.11-13
• /
• 2010

Combined with the indeterminate boundaries of spatial objects, n:m correspondences makes an object-based matching be a complex problem. In this study, we model the boundary of a polygon object with fuzzy model and describe their overlapping relations as a weighted bipartite graph. Then corresponding pairs including 1:0, 1:1, 1:n and n:m relations are identified using a spectral singular value decomposition.

• Journal of the military operations research society of Korea
• /
• v.35 no.2
• /
• pp.77-86
• /
• 2009

The encounter probability graph is measured by the chance(in percent) that a vehicle, blindly moving through a minefield, will detonate a mine. The encounter probability graph versus minefield density is presented in ROK and US Army field manual but this graph is baseless because these data had not been presented as those of live mobility or wargame. In this paper, we verified this graph building procedure model as using computer program. The result values of program are almost like those of graph. Therefore this model for our to suggest have validation, verification that a modeling demand and we convince that this model will be useful for calculating encounter probability of multiple vehicles.

• Proceedings of the KSRS Conference
• /
• 2002.10a
• /
• pp.524-529
• /
• 2002

In this paper, we report the development of two DEM (digital elevation model) generation algorithms over urban areas from an IKONOS stereo pair. One ("EpiMatch") is originally developed for SPOT images and modified for IKONOS images. It uses epipolar geometry for accurate DEM generation. The other is based on graph-cut algorithm in 3D voxel space. This algorithm is believed to work better on height discontinuities than EpiMatch. An IKONOS image pair over Taejon city area was used for tests. Using ground control points obtained from differential GPS, camera model was set up and stereo matching applied. As a result, two DEMs over urban areas were produced. Within a DEM from EpiMatch small houses appear as small "cloudy" patches and large apartment and industrial buildings are visually identifiable. Within the DEM from graph-cut we could achieve better height information on building boundaries. The results show that both algorithms can generate DEMs from IKONOS images although more research is required on handling height discontinuities (for "EpiMatch") and on faster computation (for "Graph-cut").

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.31 no.5
• /
• pp.1021-1030
• /
• 2021

This paper proposes S-CAFG(Stage-based Cyber Attack Flow Graph), a model for effectively describing training scenarios that simulate modern complex cyber attacks. On top of existing graph and tree models, we add a stage node to model more complex scenarios. In order to evaluate the proposed model, we create a complicated scenario and compare how the previous models and S-CAFG express the scenario. As a result, we confirm that S-CAFG can effectively describe various attack scenarios such as simultaneous attacks, additional attacks, and bypass path selection.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.11
• /
• pp.5731-5754
• /
• 2019

In this paper, we redesign, implement, and evaluate ShareSafe (Based on SecGraph), an open-source secure graph data sharing/publishing platform. Within ShareSafe, we propose De-anonymization Quantification Module and Recommendation Module. Besides, we model the attackers' background knowledge and evaluate the relation between graph data privacy and the structure of the graph. To the best of our knowledge, ShareSafe is the first platform that enables users to perform data perturbation, utility evaluation, De-A evaluation, and Privacy Quantification. Leveraging ShareSafe, we conduct a more comprehensive and advanced utility and privacy evaluation. The results demonstrate that (1) The risk of privacy leakage of anonymized graph increases with the attackers' background knowledge. (2) For a successful de-anonymization attack, the seed mapping, even relatively small, plays a much more important role than the auxiliary graph. (3) The structure of graph has a fundamental and significant effect on the utility and privacy of the graph. (4) There is no optimal anonymization/de-anonymization algorithm. For different environment, the performance of each algorithm varies from each other.

• Knowledge Management Research
• /
• v.10 no.2
• /
• pp.35-48
• /
• 2009

The paper proposes a quantitative causal ordering map (QCOM) to combine qualitative and quantitative methods in a framework. The procedures for developing QCOM consist of three phases. The first phase is to collect partially known causal dependencies from experts and to convert them into relations and causal nodes of a model graph. The second phase is to find the global causal structure by tracing causality among relation and causal nodes and to represent it in causal ordering graph with signed coefficient. Causal ordering graph is converted into QCOM by assigning regression coefficient estimated from path analysis in the third phase. Experiments with the prediction model of Korea stock price show results as following; First, the QCOM can support the design of qualitative and quantitative model by finding the global causal structure from partially known causal dependencies. Second, the QCOM can be used as an integration tool of qualitative and quantitative model to offerhigher explanatory capability and quantitative measurability. The QCOM with static and dynamic analysis is applied to investigate the changes in factors involved in the model at present as well discrete times in the future.