Skip to main navigation Skip to search Skip to main content

AI-powered deobfuscation: a novel approach to understanding reverse engineered code

  • Bishwajeet Pandey
  • , Sanjeev Pippal
  • , Simi Bajaj
  • , Ashish Kumar Singh
  • , Advait Patel
  • , M. K. Hasan
  • GL Bajaj Institute of Technology and Management
  • Department of CSE
  • JAIN (Deemed-to-be University)
  • Broadcom Corporation
  • Center for Cybersecurity
  • Universiti Kebangsaan Malaysia

Research output: Chapter in Book / Conference PaperConference Paperpeer-review

Abstract

In this research, we are reverse engineering an APK file using the GUI version of the JADX tool. We are receiving two folders from JADX, namely Sources and Resources. Sources contain three thousand files, and similarly, resources include hundreds of files. The source code in the source folder was in obfuscated form. To read code in an obfuscated form, we harness the power of AI by giving our code to ChatGPT and asking it to find a secret flag inside. We discovered a hidden debug flag (debug_bypass_phenotype).

Original languageEnglish
Title of host publicationProceedings of the 2025 IEEE Madhya Pradesh Section Conference (MPCON 2025), 29th - 30th August 2025, Jabalpur, India
Place of PublicationU.S.
PublisherIEEE
Pages848-851
Number of pages4
ISBN (Electronic)9798331512859
DOIs
Publication statusPublished - 2025
EventIEEE Madhya Pradesh Section Conference - Jabalpur, India
Duration: 29 Aug 202530 Aug 2025

Conference

ConferenceIEEE Madhya Pradesh Section Conference
Abbreviated titleMPCON
Country/TerritoryIndia
CityJabalpur
Period29/08/2530/08/25

Keywords

  • APK
  • ChatGPT
  • Deobfuscation using AI
  • JADX
  • Obfuscation
  • Reverse Engineering
  • Secret Flag

Fingerprint

Dive into the research topics of 'AI-powered deobfuscation: a novel approach to understanding reverse engineered code'. Together they form a unique fingerprint.

Cite this