BugGraph: Differentiating Source-Binary Code Similarity with Graph Triplet-Loss Network

Ji, Yuede; Cui, Lei; Huang, H. Howie

doi:10.1145/3433210.3437533

Cited by 24 publications

(14 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method achieves a classification accuracy of 80%. Ji et al 49 proposed a hybrid approach of Attributed Control Flow Graph (ACFG), and Graph Triplet Loss Network (GTN) to extract code similarity. The program flow is collected using ACFG, and a Tensorflow‐based GTN model is used to rank related functions across many software projects.…”

Section: Resultsmentioning

confidence: 99%

CroLSSim: Cross‐language software similarity detector using hybrid approach of LSA‐based AST‐MDrep features and CNN‐LSTM model

Ullah

Naeem

et al. 2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

Software similarity in different programming codes is a rapidly evolving field because of its numerous applications in software development, software cloning, software plagiarism, and software forensics. Currently, software researchers and developers search cross‐language open‐source repositories for similar applications for a variety of reasons, such as reusing programming code, analyzing different implementations, and looking for a better application. However, it is a challenging task because each programming language has a unique syntax and semantic structure. In this paper, a novel tool called Cross‐Language Software Similarity (CroLSSim) is designed to detect similar software applications written in different programming codes. First, the Abstract Syntax Tree (AST) features are collected from different programming codes. These are high‐quality features that can show the abstract view of each program. Then, Methods Description (MDrep) in combination with AST is used to examine the relationship among different method calls. Second, the Term Frequency Inverse Document Frequency approach is used to retrieve the local and global weights from AST‐MDrep features. Third, the Latent Semantic Analysis‐based features extraction and selection method is proposed to extract the semantic anchors in reduced dimensional space. Fourth, the Convolution Neural Network (CNN)‐based features extraction method is proposed to mine the deep features. Finally, a hybrid deep learning model of CNN‐Long‐Short‐Term Memory is designed to detect semantically similar software applications from these latent variables. The data set contains approximately 9.5K Java, 8.8K C#, and 7.4K C++ software applications obtained from GitHub. The proposed approach outperforms as compared with the state‐of‐the‐art methods.

show abstract

Section: Resultsmentioning

confidence: 99%

CroLSSim: Cross‐language software similarity detector using hybrid approach of LSA‐based AST‐MDrep features and CNN‐LSTM model

Ullah

Naeem

et al. 2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

show abstract

“…Finally, because our focus is on comparing binaries without source code, we intentionally exclude similarity comparison techniques that require source code. Nevertheless, it is noteworthy that there has been plentiful literature on comparing two source code snippets [75], [154], [155], [156], [157], [158], [159], [160], [161], [162] or comparing source snippets with binary snippets [163], [164], [165], [166].…”

Section: Discussionmentioning

confidence: 99%

Revisiting Binary Code Similarity Analysis Using Interpretable Feature Engineering and Lessons Learned

Kim

Kil

et al. 2023

IIEEE Trans. Software Eng.

View full text Add to dashboard Cite

Binary code similarity analysis (BCSA) is widely used for diverse security applications, including plagiarism detection, software license violation detection, and vulnerability discovery. Despite the surging research interest in BCSA, it is significantly challenging to perform new research in this field for several reasons. First, most existing approaches focus only on the end results, namely, increasing the success rate of BCSA, by adopting uninterpretable machine learning. Moreover, they utilize their own benchmark, sharing neither the source code nor the entire dataset. Finally, researchers often use different terminologies or even use the same technique without citing the previous literature properly, which makes it difficult to reproduce or extend previous work. To address these problems, we take a step back from the mainstream and contemplate fundamental research questions for BCSA. Why does a certain technique or a certain feature show better results than the others? Specifically, we conduct the first systematic study on the basic features used in BCSA by leveraging interpretable feature engineering on a large-scale benchmark. Our study reveals various useful insights on BCSA. For example, we show that a simple interpretable model with a few basic features can achieve a comparable result to that of recent deep learning-based approaches. Furthermore, we show that the way we compile binaries or the correctness of underlying binary analysis tools can significantly affect the performance of BCSA. Lastly, we make all our source code and benchmark public and suggest future directions in this field to help further research.

show abstract

“…The works that consider the CFG from a graph perspective and apply deep learning methods to represent the CFG are described in the following. The attributed Control Flow Graph (ACFG) is a common preprocessing step in some of the following works, especially in binary code similarity detection, such as Genius [49], Gemini [178] and BugGraph [75]. There are also some typical modifications for CFG, for example, lazy-binding CFG [121], inter-procedural CFGs(ICFG) [47].…”

Section: Flow-graph-based Structuresmentioning

confidence: 99%

“…GAT extracts the context information for each statement, which is modeled by the events that are embedded to capture execution semantics. BugGraph [75] compares the source-binary code similarity in two steps: source binary canonicalization and code similarity computation. In the code similarity computation step, BugGraph computes the similarity between the target and the comparing binary code.…”

Section: Flow-graph-based Structuresmentioning

confidence: 99%

A Survey of Deep Learning Models for Structural Code Understanding

Wu¹,

Zhang²,

Peng³

et al. 2022

Preprint

View full text Add to dashboard Cite

In recent years, the rise of deep learning and automation requirements in the software industry has elevated Intelligent Software Engineering to new heights. The number of approaches and applications in code understanding is growing, with deep learning techniques being used in many of them to better capture the information in code data. In this survey, we present a comprehensive overview of the structures formed from code data. We categorize the models for understanding code in recent years into two groups: sequence-based and graph-based models, further make a summary and comparison of them 1 . We also introduce metrics, datasets and the downstream tasks. Finally, we make some suggestions for future research in structural code understanding field.

show abstract

BugGraph: Differentiating Source-Binary Code Similarity with Graph Triplet-Loss Network

Cited by 24 publications

References 42 publications

CroLSSim: Cross‐language software similarity detector using hybrid approach of LSA‐based AST‐MDrep features and CNN‐LSTM model

CroLSSim: Cross‐language software similarity detector using hybrid approach of LSA‐based AST‐MDrep features and CNN‐LSTM model

Revisiting Binary Code Similarity Analysis Using Interpretable Feature Engineering and Lessons Learned

A Survey of Deep Learning Models for Structural Code Understanding

Contact Info

Product

Resources

About