5 papers · 1 filter
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…
Overeager Coding Agents: Measuring Out-of-Scope Actions on Benign Tasks
Yubin Qu, Ying Zhang, Yanjun Zhang +4
Coding agents now run autonomously with shell, file, and network privileges. When a user issues a benign request, the agent sometimes does more than asked: it deletes unrelated fil…
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…
Drowzee: Metamorphic Testing for Fact-Conflicting Hallucination Detection in Large Language Models
Ningke Li, Yuekang Li, Yi Liu +3
Large language models (LLMs) have transformed the landscape of language processing, yet struggle with significant challenges in terms of security, privacy, and the generation of se…
MeTMaP: Metamorphic Testing for Detecting False Vector Matching Problems in LLM Augmented Generation
Guanyu Wang, Yuekang Li, Yi Liu +6
Augmented generation techniques such as Retrieval-Augmented Generation (RAG) and Cache-Augmented Generation (CAG) have revolutionized the field by enhancing large language model (L…