OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows

תקציר מקורי באנגליתarXiv:2510.24411v3 Announce Type: replace-cross Abstract: Computer-using agents powered by Vision-Language Models (VLMs) have demonstrated human-like capabilities in operating digital environments like mobile platforms. While these agents hold great promise for advancing digital automation, their potential for unsafe operations, such as system compromise and privacy leakage, is raising significant concerns. Detecting these safety concerns across the vast and complex operational space of mobile environments presents a formidable challenge that remains critically underexplored. To establish a foundation for mobile agent safety research, we introduce MobileRisk-Live, a dynamic sandbox environment accompanied by a safety detection benchmark comprising realistic trajectories with fine-grained a