2 papers
cs.SE2026
Mind your key: An Empirical Study of LLM API Credential Leakage in iOS Apps
Pinran Gao, Lingxiang Wang, Yi Liu +3
The rapid integration of large language models (LLMs) into mobile applications has introduced a new class of credential security risk: leaked credentials that grant unauthorized ac…
cs.SE2025
CognixShield: PoV-Guided Vulnerable API Usage Detection in Large Codebases via LLMs
Wang Lingxiang, Quanzhi Fu, Wenjia Song +4
The integration of open-source libraries in Java development introduces severe security risks through vulnerable APIs. Existing program analysis and deep learning tools face the ch…