17 papers
Evaluating LLMs for Obfuscation Detection and Classification in Android Apps
Luca Ferrari, Marco Alecci, Jordan Samhi +4
Android applications (apps) developers increasingly rely on code obfuscation techniques to hinder reverse engineering and protect intellectual property. However, obfuscation also r…
Neural Change Prediction: Relating Software Changes to Their Effects and Vice Versa
Laura Plein, Souhila Zidane, Jordan Samhi +1
Much of software development revolves around understanding the relationship between software changes and their effects. If we could learn and predict those relationships, such pred…
From Rookie to Expert: Manipulating LLMs for Automated Vulnerability Exploitation in Enterprise Software
Moustapha Awwalou Diouf, Maimouna Tamah Diao, Iyiola Emmanuel Olatunji +6
LLMs democratize software engineering by enabling non-programmers to create applications, but this same accessibility fundamentally undermines security assumptions that have guided…
Learned or Memorized ? Quantifying Memorization Advantage in Code LLMs
Djiré Albérick Euraste, Kaboré Abdoul Kader, Jordan Samhi +3
The lack of transparency about code datasets used to train large language models (LLMs) makes it difficult to detect, evaluate, and mitigate data leakage. We present a perturbation…
GAPS: Targeted Execution of Android Apps via Static Path Reconstruction
Samuele Doria, Eleonora Losiouk, Alexander Pilgun +2
Targeted execution of Android applications (apps) remains a longstanding challenge for software testing and analysis. Although recent advances in GUI testing have substantially imp…
Exploring Hidden Geographic Disparities in Android Apps
M. Alecci, P. Jiménez, J. Samhi +2
While mobile app evolution has been widely studied, geographical variation in app behavior remains largely unexplored. This paper presents a large-scale study of location-based And…