106 citations · 116 across the 9 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.CR2026
PriMobiBench: Characterizing Visual Privacy Leakage in VLM-Driven Mobile GUI Agents
Qihang Cen, Tianshuo Cong, Da Song +4
Mobile GUI agents increasingly rely on Vision-Language Models (VLMs) to automate smartphone tasks by interpreting screenshot streams. However, this design introduces serious and un…
cs.CL2026
Evaluating Implicit Regulatory Compliance in LLM Tool Invocation via Logic-Guided Synthesis
Da Song, Yuheng Huang, Boqi Chen +4
The integration of large language models (LLMs) into autonomous agents has enabled complex tool use, yet in high-stakes domains, these systems must strictly adhere to regulatory st…