Master Thesis Proposal

UNO Reverse Card: Hardening Android App against AI-based Reverse Engineering

1 Problem Statement

Reverse engineering through AI-based tools, such as Claude Code and Reverse Engineer Anything, is a hot topic. In November 2026, Claude disabled their AI from reverse engineering specific products like smart TVs, video games, and even Adobe Photoshop, pressured by companies. While these examples are the most egregious, Android apps have also become far easier to reverse engineer. Traditional countermeasures, such as code obfuscation (e.g., ProGuard), still work on AI-based tools, but are far less effective that before when humans did the job. We plan to investigate new, specific techniques to prevent AIbased reverse engineering, or at least make it more expensive. We will borrow knowledge from existing works, but will also need to bake our own custom solutions, as the Android domain is very peculiar compared to others (e.g., DEX/SMALI code can be more easily decompiled than C).

2 Project Plan

  1. Literature Review: The student will study prior research on AI-based reverse engineering and Android-specific countermeasures.
  2. Experimental Testbed: The student will select Android apps to reverse engineer (as the targets), and collect tools and techniques to evaluate AIbased reverse engineering.
  3. Evaluation: The student will pick relevant metrics and evaluate the performances of AI-based reverse engineering on their testbed.
  4. Hardening Solution Proposal: The student will design, implement, and evaluate a hardening solution that makes AI-based reverse engineering more challenging.

3 Ideal Background

You are interested in mobile and AI security and privacy. This project builds
upon research works authored by the supervisor (Marco Casagrande). You will have a chance to test your skills, add an impactful project to your CV, learn state-of-the-art reverse engineering techniques, and break real-world Android devices.
Relevant Skills. Proficiency in programming and scripting languages, such
as Python, Java, and JavaScript. Basic knowledge of security and privacy,
Android, and AI. Optionally, experience with reverse engineering.

4 Thesis Supervisor

Marco Casagrande is a postdoc in cybersecurity at Orebro University. He spe- cializes in Android security and reverse engineering. He is passionate about hands-on, hacking-oriented research. In addition to his academic publications, he has been invited to speak at several prominent hacking conferences, including Black Hat USA, DEF CON, and Hardwear.io. He is deeply involved in bug hunting, reporting vulnerabilities to market leaders such as Google, Xiaomi, and the FIDO Alliance.

Annonsuppgifter

Annonsör: Örebro universitet

Ansök senast:

Annonskategori: Examensarbete, praktik, uppsats

Intresseområde: Data och IT

Kontaktperson: Alberto Giaretta (Assistant Professor) alberto.giaretta@oru.se

Webbsida: https://www.oru.se/