• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권8호
• /
• 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.

• 한국컴퓨터정보학회논문지
• /
• 제21권12호
• /
• pp.1-10
• /
• 2016

In this paper, we attempt to prevent certain cases by tracing a history and making genogram about open source software and its modification using similarity of source code. There are many areas which use open source software actively and widely, and open source software contributes their development. However, there are many unconscious cases like ignoring license or intellectual properties infringe which can lead litigation. To prevent such situation, we analyze source code similarity using program dependence graph which resembles subgraph isomorphism problem, a typical NP-complete problem. To solve subgraph isomorphism problem, we utilized harmony search of metaheuristic algorithm and compared its result with a genetic algorithm. For the future works, we represent open source software as program dependence graph and analyze their similarity.

• Journal of Information Processing Systems
• /
• 제13권5호
• /
• pp.1158-1167
• /
• 2017

Many real-world applications information are organized and represented with graph structure which is often used for representing various ubiquitous networks, such as World Wide Web, social networks, and protein-protein interactive networks. In particular, similarity evaluation between graphs is a challenging issue in many fields such as graph searching, pattern discovery, neuroscience, chemical compounds exploration and so forth. There exist some algorithms which are based on vertices or edges properties, are proposed for addressing this issue. However, these algorithms do not take both vertices and edges similarities into account. Towards this end, this paper pioneers a novel approach for similarity evaluation between graphs based on formal concept analysis. The feature of this approach is able to characterize the relationships between nodes and further reveal the similarity between graphs. Therefore, the highlight of our approach is to take vertices and edges into account simultaneously. The proposed algorithm is evaluated using a case study for validating the effectiveness of the proposed approach on detecting and measuring the similarity between graphs.

• 대한의용생체공학회:의공학회지
• /
• 제38권2호
• /
• pp.82-88
• /
• 2017

Enlargement of the lateral ventricles have been identified as a surrogate marker of neurological disorders. Quantitative measure of the lateral ventricle from MRI would enable earlier and more accurate clinical diagnosis in monitoring disease progression. Even though it requires an automated or semi-automated segmentation method for objective quantification, it is difficult to define lateral ventricles due to insufficient contrast and brightness of structural imaging. In this study, we proposed a fully automated lateral ventricle segmentation method based on a graph cuts algorithm combined with atlas-based segmentation and connected component labeling. Initially, initial seeds for graph cuts were defined by atlas-based segmentation (ATS). They were adjusted by partial volume images in order to provide accurate a priori information on graph cuts. A graph cuts algorithm is to finds a global minimum of energy with minimum cut/maximum flow algorithm function on graph. In addition, connected component labeling used to remove false ventricle regions. The proposed method was validated with the well-known tools using the dice similarity index, recall and precision values. The proposed method was significantly higher dice similarity index ($0.860{\pm}0.036$, p < 0.001) and recall ($0.833{\pm}0.037$, p < 0.001) compared with other tools. Therefore, the proposed method yielded a robust and reliable segmentation result.

• 한국지능시스템학회논문지
• /
• 제15권6호
• /
• pp.759-764
• /
• 2005

본 논문은 EBGM(Elastic Bunch Graph Matching)기법을 이용한 얼굴인식에 대해 다룬다. 대용량 영상 정보에 대해 차원 축소를 이용한 얼굴인식 기법인 주성분기법이나 선형판별기법에서는 얼굴 영상 전체의 정보를 이용하는 반면 본 연구에서는 얼굴의 눈 코 입 등과 같은 얼굴 특징점에 대해 주파수와 방향각이 다른 여러 개의 가버 커널과 영상 이미지의 컨볼루션(Convolution)의 계수의 집합(Jets)을 이용한 특징 데이터를 이용한다. 하나의 얼굴 영상에 대해서 모든 영상이 같은 크기의 특질 데이터로 표현되는 Face Graph가 생성되며, 얼굴인식 과정에서는 추출된 제트의 집합에 대해서 상호 유사도(Similarity)의 크기를 비교하여 얼굴인식을 수행한다. 본 논문에서는 기존의 EBGM 방법의 Face Graph 생성 과정을 보다간략화 한 방법을 이용하여 얼굴인식 과정에서 계산량을 줄여 속도를 개선하였으며, 퍼지 매칭법을 이용한 유사도 계산을 하였다.

• 한국콘텐츠학회논문지
• /
• 제9권2호
• /
• pp.142-151
• /
• 2009

기존의 문서 군집화 기법 NSTC은 문서 군집화 과정 내에서 TF-IDF를 이용하여 문서간 유사도를 측정한다. 본 논문에서는 TF-IDF가 아닌, 공통 Phrase의 관계 그래프를 이용한 새로운 문서간 유사도 측정을 제안한다. 이 방법은 문서 집합 내의 공통 Phrase들의 관계를 나타낸 관계 그래프를 통해 공통 Phrase의 가중치를 부여하는 방법을 제시한다. 또한 실험을 통해 NSTC와 비교하여 본 논문에서 제안한 문서간 유사도 측정 기법이 문서 군집화에 더욱 효과적임을 보였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제6권5호
• /
• pp.1463-1478
• /
• 2012

Based on the theory of local-world network, the composition self-similarity (CSS) of network traffic is presented for the first time in this paper for the study of DoS detection. We propose the concept of composition distribution graph and design the relative operations. The $(R/S)^d$ algorithm is designed for calculating the Hurst parameter. Based on composition distribution graph and Kullback Leibler (KL) divergence, we propose the composition self-similarity anomaly detection (CSSD) method for the detection of DoS attacks. We evaluate the effectiveness of the proposed method. Compared to other entropy based anomaly detection methods, our method is more accurate and with higher sensitivity in the detection of DoS attacks.

• 한국CDE학회논문집
• /
• 제16권1호
• /
• pp.21-30
• /
• 2011

Similarity assessment of a CAD model is one of important issues from the aspect of model re-using. In real practice, many new mechanical parts are designed by modifying existing ones. The reuse of part enables to save design time and efforts for the designers. Design time would be further reduced if there were an efficient way to search for existing similar designs. This paper proposes an efficient algorithm of similarity assessment for mechanical part model with design history embedded within the CAD model. Since it is possible to retrieve the design history and detailed-feature information using CAD API, we can obtain an accurate and reliable assessment result. For our purpose, our assessment algorithm can be divided by two: (1) we select suitable parts by comparing MSG (Model Signature Graph) extracted from a base feature of the required model; (2) detailed-features' similarities are assessed with their own attributes and reference structures. In addition, we also propose a indexing method for managing a model database in the last part of this article.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제32권4호
• /
• pp.290-299
• /
• 2005

컴퓨터와 소프트웨어의 사용이 증가하면서, 프로그램 소스의 도용(표절)이 사회적인 문제로 부각되고 있다. 이런 문제를 해결하고자 프로그램의 문법 구조를 비교하여 표절을 찾아내는 방법론이 제안되었지만, 간단한 프로그램 수정에도 표절을 찾아내지 못하는 한계를 가지고 있다 이 연구에서는, 문법 구조적인 정보 뿐 아니라, 프로그램식 간의 수행시 의존 관계를 드러내는 그래프를 이용한 프로그램 표절 감지 시스템을 제안한다. 이 방법론은 문법 정보 뿐 아니라, 수행시 의존 관계까지 비교 대상에 을림으로써, 수행시 의콘 관계를 변화시키지 못하는 프로그램 수정에 대해서도 프로그램 표절을 판별할 수 있다. 또한, 이 연구에서는 표절 프로그램이란 무엇인가를 엄밀하게 정의하고 이 표절 프로그램의 정의와 연구에서 제안된 표:늰 감별 그래프와의 관계를 보였다. 즉, 두 프로그램이 표절이라는 것은 표절 감별 그래프가 일치한다는 긴과 필요 충분 관계가 있음을 증명하였다. 또한 제안된 표절 감별 방법론을 실제적인 프로그래밍 언어인 IML 에 대해서 구현하였다. 구현된 도구를 통해서 실제 표절된 프로그램들을 감별한 결과, 기존의 방법에서 찾기 어려운 프로그램 표절을 제안된 방법론이 다룰 수 있음을 확인하였다.

• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.752-759
• /
• 2022

The instantiation of spaces as a discrete entity allows users to utilize BIM models in a wide range of analyses. However, in practice, their utility has been limited as spaces are erroneously entered due to human error and often omitted entirely. Recent studies attempted to automate space allocation using artificial intelligence approaches. However, there has been limited success as most studies focused solely on the use of geometric features to distinguish spaces. In this study, in addition to geometric features, semantic relations between spaces and elements were modeled and used to improve space classification in BIM models. Graph Convolutional Networks (GCN), a deep learning algorithm specifically tailored for learning in graphs, was deployed to classify spaces via a similarity graph that represents the relationships between spaces and their surrounding elements. Results confirmed that accuracy (ACC) was +0.08 higher than the baseline model in which only geometric information was used. Most notably, GCN was able to correctly distinguish spaces with no apparent difference in geometry by discriminating the specific elements that were provided by the similarity graph.