lac-dcc/yali

A framework to analyze a space formed by the combination of program encodings, obfuscation passes and stochastic classification models.

31
/ 100
Emerging

This project helps software security researchers and reverse engineers evaluate how well deep learning models can classify programs that have been intentionally obfuscated. You provide program code in various representations and obfuscation levels, and it outputs an analysis of how different classification models perform, particularly how their accuracy is affected by obfuscation. It's designed for those who need to understand the resilience of program classification systems against common code protection techniques.

No commits in the last 6 months.

Use this if you are a researcher or security professional investigating the effectiveness of deep learning models in classifying obfuscated source code and want to systematically test various program representations and obfuscation strategies.

Not ideal if you are looking for a tool to obfuscate code, detect malware in live systems, or analyze the performance of general software without a focus on deep learning model resilience to obfuscation.

program-analysis software-security reverse-engineering code-obfuscation deep-learning-robustness
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

36

Forks

3

Language

LLVM

License

GPL-3.0

Last pushed

Aug 01, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/lac-dcc/yali"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.