Automated Vulnerability detection for software using NLP techniques
Vulnerabilities can have devastating effects for information security, with farreaching ramifications for the economy, social security, and even national security. One of the most anticipated researches in the field of vulnerability detection is the use of some of the most cutting-edge NLP technologies to create models and accomplish the automatic analysis and detection of source code for particular text files such as source code. The proposed a deep learning-based vulnerability detection algorithm that extracts features using an RNN composite neural network. The employ a SARD and NVD dataset of lots of open source roles, which will be tagged with results after three static analyzers that hint to possible activities. By this dataset, develop a fast and accessible vulnerability detection system built on deep feature sign knowledge that directly translates source code. Our findings suggest that deep feature representation learning on source-code could be used to automatically uncover software vulnerabilities. In this study, the model software vulnerability detection as a natural language processing (NLP) problem with source code handled as texts, and use advanced deep learning NLP models with transfer learning on written English to address automated software vulnerability detection. Different algorithms will be compared (machine learning and deep learning).
Copyright (c) 2021 Journal of Information Communication Technologies and Robotic Applications
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.