Context-Aware Functional Modeling for Android Third-Party Library Detection
LibFan detects partial Android libraries under heavy obfuscation, beating prior detectors on a new benchmark.
LibFan is a learning-based Android third-party library detector that combines method-level context-aware contrastive learning with library-level functional partitioning. Call relationships and class context are intended to resist obfuscation, shrinking, and optimization, while best-matching partitions handle apps that retain only part of a library. On a benchmark of 200 apps and 46 vulnerable TPLs compiled under four transformation settings, R8 full mode yielded F1 scores of 81.3% at library level and 47.6% at version level, relative gains of 64.9% and 35.6% over prior work.
- Method embeddings use outgoing calls and class context against code transforms.
- Functional partitions let detection succeed when only part of a library remains.
- Benchmark uses 200 apps and 46 vulnerable TPLs under four build settings.
- R8 full mode F1 is 81.3% at library level and 47.6% at version level.
From the original article
1 min read at arxiv.orgThird-party libraries (TPLs) are widely used in Android apps, but their reuse can introduce security risks and interfere with downstream program analyses. Existing Android TPL detection approaches face two key limitations: their hand-crafted features are fragile under aggressive code transformations, and their whole-library matching strategies are ineffective when apps retain only part of a TPL.
By Dihao Fan · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.