Summary of A Survey Of Source Code Representations For Machine Learning-based Cybersecurity Tasks, by Beatrice Casey et al.
A Survey of Source Code Representations for Machine Learning-Based Cybersecurity Tasks
by Beatrice Casey, Joanna C. S. Santos, George Perry
First submitted to arxiv on: 15 Mar 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Cryptography and Security (cs.CR)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper presents a study on machine learning-based approaches for cybersecurity-related software engineering tasks, focusing on source code representations and their impact on model performance. The authors investigate existing techniques, identifying trends in representation types (e.g., graph-based, Tokenizers, Abstract Syntax Trees) and models used (e.g., sequence-based, Support Vector Machines). The study reveals that vulnerability detection is the most popular cybersecurity task, while C is the language covered by the most techniques. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper looks at how machine learning helps with writing safer computer code. It checks out what kind of “code recipes” people use to make their models work better. They find that some ways of representing code (like graphs) are really popular, as well as using special tools like Tokenizers and Abstract Syntax Trees. The most common task is finding vulnerabilities in code, and the language C is used in many techniques. |
Keywords
» Artificial intelligence » Machine learning » Syntax
