BLSTM-based source code vulnerability detection visualization system

Zhili Ma; Hongzhong Ma; Xiang Gao; Teli Cai; Xuejun Zhang

doi:10.1117/12.2624204

19 December 2021 BLSTM-based source code vulnerability detection visualization system

Zhili Ma, Hongzhong Ma, Xiang Gao, Teli Cai, Xuejun Zhang

Proceedings Volume 12128, Second International Conference on Industrial IoT, Big Data, and Supply Chain; 121280W (2021) https://doi.org/10.1117/12.2624204
Event: 2nd International Conference on Industrial IoT, Big Data, and Supply Chain, 2021, Macao, China

Abstract

A visualization system with source code vulnerability detection is constructed based on the deep learning BLSTM model. The system firstly has the static analysis and slicing capabilities of the vulnerability statement, and then based on the deep learning model of the recurrent neural network and the attention mechanism technology, it can learn from the vulnerability data set the characteristics of the vulnerability and the realization of vulnerability detection. Firstly, the system analyzes the source code through the deployed open-source static analysis tool Joern according to the code to be tested, and stores the generated code attribute graph in the Neo4J graph database, then slices the program code according to the API call. The sliced code is treated as a text, which is mapped into a vector using word embedding technology, and finally input into the BLSTM model to determine whether there is vulnerability in the code under test. Through the visual interface, the system can interact with the user, and the user can independently select and train the model. Through experimental analysis and testing, the system has achieved good results.

Citation Download Citation

Zhili Ma, Hongzhong Ma, Xiang Gao, Teli Cai, and Xuejun Zhang "BLSTM-based source code vulnerability detection visualization system", Proc. SPIE 12128, Second International Conference on Industrial IoT, Big Data, and Supply Chain, 121280W (19 December 2021); https://doi.org/10.1117/12.2624204

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
9 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Data modeling

Visualization

Visual process modeling

Software development

Human-machine interfaces

Statistical modeling

Systems modeling

Show All Keywords

Keywords/Phrases

Search In:

Publication Years