EUVIMEDEUVIMED entdecken
Crossref

TaskFlow: LLMs for Android Taint Specification

Marco Alecci, Jordan Samhi, Marc Miltenberger, Steven Arzt, Tegawendé F. Bissyandé, Jacques Klein

ACM Transactions on Software Engineering and Methodology · 15.05.2026

DOI: 10.1145/3815184 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Software Engineering and Methodology, online erschienen am 15.05.2026. Verfasst von Marco Alecci und 5 weiteren Autor:innen. Die Arbeit nennt 53 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Taint analysis is a widely used technique to analyze Android apps, enabling the tracking of data flow within an app. A key step consists in identifying which methods act as SOURCEs (i.e., where a data of interest originates) and SINKs (where data might be exposed). Existing approaches typically fall into two categories: ➀ Handcrafted lists, which suffer from incompleteness and quickly become outdated; and ➁ Automated techniques, which, although scalable, over-approximate and produce many false positives, primarily due to the challenge of defining what qualifies as a SOURCE . While identifying SINKs is generally more straightforward (as they correspond to explicit exposure points), defining a universal criterion for what constitutes a SOURCE remains inherently challenging. For example, isMicrophoneMute () may not typically be considered a SOURCE , yet in specific contexts it could represent a significant privacy concern. This context dependence highlights the limitations of static, generic lists of SOURCE methods. We present TaskFlow , a novel LLM-driven framework for generating task-specific lists of SOURCE (or SINK ) methods aligned with specific analysis goals. By reasoning over API semantics and contextual usage, TaskFlow ➀ mitigates the noise commonly introduced by overly broad lists, leading to more precise taint analyses; and ➁ addresses the incompleteness of manual approaches.

Zitieren

APA

Alecci, M., Samhi, J., Miltenberger, M., Arzt, S., Bissyandé, T. F., & Klein, J. (2026). TaskFlow: LLMs for Android Taint Specification. ACM Transactions on Software Engineering and Methodology. https://doi.org/10.1145/3815184

Vancouver

Alecci M, Samhi J, Miltenberger M, Arzt S, Bissyandé TF, Klein J. TaskFlow: LLMs for Android Taint Specification. ACM Transactions on Software Engineering and Methodology. 2026. doi:10.1145/3815184

BibTeX
@article{Alecci2026,
  author = {Alecci, Marco and Samhi, Jordan and Miltenberger, Marc and Arzt, Steven and Bissyandé, Tegawendé F. and Klein, Jacques},
  title = {TaskFlow: LLMs for Android Taint Specification},
  journal = {ACM Transactions on Software Engineering and Methodology},
  year = {2026},
  doi = {10.1145/3815184}
}
Kostenlos starten →