AppBDS: LLM-Powered Description Synthesis for Sensitive Behaviors in Mobile Apps
Zichen Liu, Xusheng Xiao
Abstract
As mobile applications (i.e., apps) increasingly manage a wide variety of user needs, their access to sensitive data intensifies privacy concerns among users. While app markets employ permissions to regulate private data access, the lack of explanation for permission usage renders this mechanism less effective. Existing techniques that extract explanatory sentences from app descriptions to inform users about sensitive behaviors are also limited. Many app behaviors remain unexplained in app descriptions. To address these issues, we propose AppBDS, a novel approach that integrates program analysis with Large Language Models (LLMs) to process code semantics and UI contexts, further complemented by privacy policies and information from similar apps, in order to generate detailed explanations for apps’ sensitive behaviors. Specifically, AppBDS integrates code semantics with UI contexts to build a UI-Fused Call Graph (UCG) for each app. Additionally, AppBDS summarizes permission-related propositions from privacy policies and utilizes similar apps’ information from a knowledge base (PP-KB) to improve LLMs’ domain knowledge in explaining permission usage. Our evaluation on 270 real-world apps demonstrates that AppBDS significantly outperforms state-of-the-art approaches in richness, specificity, and semantic relatedness, while also proving highly robust against common code obfuscation.
Ask Lune
Know where this paper stands in minutes, not an afternoon.
Lune can read the top-tier papers that cite it and the ones closest to it, and tells you what it claims, what came after and where it falls short, each point cited to the paper it comes from. No skimming, no AI slop.
Related papers
- DescribeCtx: Context-Aware Description Synthesis for Sensitive Behaviors in Mobile AppsShao Yang, Yuehan Wang, Yuan Yao, Haoyu Wang et al.ICSE 2022 · 8 citations
- Automated Program Repair for UI-Centric Android Bugs: How Far Are We?Junayed Mahmud, Sparsh Pandey, Nadeeshan De Silva, Atish Kumar Dipongkor et al.ISSTA 2026
- OptiMine: Scalable and Precise Code Optimization for Android Apps via LLM-Driven Semantic AnalysisPengbo Du, Qiuping Yi, Liangzheng Zhang, Hongliang LiangISSTA 2026
- Automatic Macro Mining from Interaction Traces at ScaleForrest Huang, Gang Li, Tao Li, Yang LiCHI 2024 · 11 citations
- DeepIntent: Deep Icon-Behavior Learning for Detecting Intention-Behavior Discrepancy in Mobile AppsShengqu Xi, Shao Yang, Xusheng Xiao, Yuan Yao et al.CCS 2019 · 74 citations
