CASCADE: LLM-Powered JavaScript Deobfuscator at Google

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiang, Shan, Kovuri, Pranoy, Tao, David, Tan, Zhixun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917300139982848
author Jiang, Shan
Kovuri, Pranoy
Tao, David
Tan, Zhixun
author_facet Jiang, Shan
Kovuri, Pranoy
Tao, David
Tan, Zhixun
contents Software obfuscation, particularly prevalent in JavaScript, hinders code comprehension and analysis, posing significant challenges to software testing, static analysis, and malware detection. This paper introduces CASCADE, a novel hybrid approach that integrates the advanced coding capabilities of Gemini with the deterministic transformation capabilities of a compiler Intermediate Representation (IR), specifically JavaScript IR (JSIR). By employing Gemini to identify critical prelude functions, the foundational components underlying the most prevalent obfuscation techniques, and leveraging JSIR for subsequent code transformations, CASCADE effectively recovers semantic elements like original strings and API names, and reveals original program behaviors. This method overcomes limitations of existing static and dynamic deobfuscation techniques, eliminating hundreds to thousands of hardcoded rules while achieving reliability and flexibility. CASCADE is already deployed in Google's production environment, demonstrating substantial improvements in JavaScript deobfuscation efficiency and reducing reverse engineering efforts.
format Preprint
id arxiv_https___arxiv_org_abs_2507_17691
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CASCADE: LLM-Powered JavaScript Deobfuscator at Google
Jiang, Shan
Kovuri, Pranoy
Tao, David
Tan, Zhixun
Software Engineering
Artificial Intelligence
Cryptography and Security
Machine Learning
Programming Languages
Software obfuscation, particularly prevalent in JavaScript, hinders code comprehension and analysis, posing significant challenges to software testing, static analysis, and malware detection. This paper introduces CASCADE, a novel hybrid approach that integrates the advanced coding capabilities of Gemini with the deterministic transformation capabilities of a compiler Intermediate Representation (IR), specifically JavaScript IR (JSIR). By employing Gemini to identify critical prelude functions, the foundational components underlying the most prevalent obfuscation techniques, and leveraging JSIR for subsequent code transformations, CASCADE effectively recovers semantic elements like original strings and API names, and reveals original program behaviors. This method overcomes limitations of existing static and dynamic deobfuscation techniques, eliminating hundreds to thousands of hardcoded rules while achieving reliability and flexibility. CASCADE is already deployed in Google's production environment, demonstrating substantial improvements in JavaScript deobfuscation efficiency and reducing reverse engineering efforts.
title CASCADE: LLM-Powered JavaScript Deobfuscator at Google
topic Software Engineering
Artificial Intelligence
Cryptography and Security
Machine Learning
Programming Languages
url https://arxiv.org/abs/2507.17691